diff --git a/.yarn/patches/@ai-sdk-huggingface-npm-0.0.4-8080836bc1.patch b/.yarn/patches/@ai-sdk-huggingface-npm-0.0.4-8080836bc1.patch
new file mode 100644
index 0000000000..7aeb4ea9cf
--- /dev/null
+++ b/.yarn/patches/@ai-sdk-huggingface-npm-0.0.4-8080836bc1.patch
@@ -0,0 +1,131 @@
+diff --git a/dist/index.mjs b/dist/index.mjs
+index b3f018730a93639aad7c203f15fb1aeb766c73f4..ade2a43d66e9184799d072153df61ef7be4ea110 100644
+--- a/dist/index.mjs
++++ b/dist/index.mjs
+@@ -296,7 +296,14 @@ var HuggingFaceResponsesLanguageModel = class {
+       metadata: huggingfaceOptions == null ? void 0 : huggingfaceOptions.metadata,
+       instructions: huggingfaceOptions == null ? void 0 : huggingfaceOptions.instructions,
+       ...preparedTools && { tools: preparedTools },
+-      ...preparedToolChoice && { tool_choice: preparedToolChoice }
++      ...preparedToolChoice && { tool_choice: preparedToolChoice },
++      ...(huggingfaceOptions?.reasoningEffort != null && {
++        reasoning: {
++          ...(huggingfaceOptions?.reasoningEffort != null && {
++            effort: huggingfaceOptions.reasoningEffort,
++          }),
++        },
++      }),
+     };
+     return { args: baseArgs, warnings };
+   }
+@@ -365,6 +372,20 @@ var HuggingFaceResponsesLanguageModel = class {
+           }
+           break;
+         }
++        case 'reasoning': {
++          for (const contentPart of part.content) {
++            content.push({
++              type: 'reasoning',
++              text: contentPart.text,
++              providerMetadata: {
++                huggingface: {
++                  itemId: part.id,
++                },
++              },
++            });
++          }
++          break;
++        }
+         case "mcp_call": {
+           content.push({
+             type: "tool-call",
+@@ -519,6 +540,11 @@ var HuggingFaceResponsesLanguageModel = class {
+                   id: value.item.call_id,
+                   toolName: value.item.name
+                 });
++              } else if (value.item.type === 'reasoning') {
++                controller.enqueue({
++                  type: 'reasoning-start',
++                  id: value.item.id,
++                });
+               }
+               return;
+             }
+@@ -570,6 +596,22 @@ var HuggingFaceResponsesLanguageModel = class {
+               });
+               return;
+             }
++            if (isReasoningDeltaChunk(value)) {
++              controller.enqueue({
++                type: 'reasoning-delta',
++                id: value.item_id,
++                delta: value.delta,
++              });
++              return;
++            }
++
++            if (isReasoningEndChunk(value)) {
++              controller.enqueue({
++                type: 'reasoning-end',
++                id: value.item_id,
++              });
++              return;
++            }
+           },
+           flush(controller) {
+             controller.enqueue({
+@@ -593,7 +635,8 @@ var HuggingFaceResponsesLanguageModel = class {
+ var huggingfaceResponsesProviderOptionsSchema = z2.object({
+   metadata: z2.record(z2.string(), z2.string()).optional(),
+   instructions: z2.string().optional(),
+-  strictJsonSchema: z2.boolean().optional()
++  strictJsonSchema: z2.boolean().optional(),
++  reasoningEffort: z2.string().optional(),
+ });
+ var huggingfaceResponsesResponseSchema = z2.object({
+   id: z2.string(),
+@@ -727,12 +770,31 @@ var responseCreatedChunkSchema = z2.object({
+     model: z2.string()
+   })
+ });
++var reasoningTextDeltaChunkSchema = z2.object({
++  type: z2.literal('response.reasoning_text.delta'),
++  item_id: z2.string(),
++  output_index: z2.number(),
++  content_index: z2.number(),
++  delta: z2.string(),
++  sequence_number: z2.number(),
++});
++
++var reasoningTextEndChunkSchema = z2.object({
++  type: z2.literal('response.reasoning_text.done'),
++  item_id: z2.string(),
++  output_index: z2.number(),
++  content_index: z2.number(),
++  text: z2.string(),
++  sequence_number: z2.number(),
++});
+ var huggingfaceResponsesChunkSchema = z2.union([
+   responseOutputItemAddedSchema,
+   responseOutputItemDoneSchema,
+   textDeltaChunkSchema,
+   responseCompletedChunkSchema,
+   responseCreatedChunkSchema,
++  reasoningTextDeltaChunkSchema,
++  reasoningTextEndChunkSchema,
+   z2.object({ type: z2.string() }).loose()
+   // fallback for unknown chunks
+ ]);
+@@ -751,6 +813,12 @@ function isResponseCompletedChunk(chunk) {
+ function isResponseCreatedChunk(chunk) {
+   return chunk.type === "response.created";
+ }
++function isReasoningDeltaChunk(chunk) {
++  return chunk.type === 'response.reasoning_text.delta';
++}
++function isReasoningEndChunk(chunk) {
++  return chunk.type === 'response.reasoning_text.done';
++}
+ 
+ // src/huggingface-provider.ts
+ function createHuggingFace(options = {}) {
diff --git a/package.json b/package.json
index d846f69d3a..8da959d182 100644
--- a/package.json
+++ b/package.json
@@ -103,6 +103,7 @@
     "@agentic/tavily": "^7.3.3",
     "@ai-sdk/amazon-bedrock": "^3.0.35",
     "@ai-sdk/google-vertex": "^3.0.40",
+    "@ai-sdk/huggingface": "patch:@ai-sdk/huggingface@npm%3A0.0.4#~/.yarn/patches/@ai-sdk-huggingface-npm-0.0.4-8080836bc1.patch",
     "@ai-sdk/mistral": "^2.0.19",
     "@ai-sdk/perplexity": "^2.0.13",
     "@ant-design/v5-patch-for-react-19": "^1.0.3",
diff --git a/packages/aiCore/src/core/providers/schemas.ts b/packages/aiCore/src/core/providers/schemas.ts
index f5a8b60a29..0d507d5cc6 100644
--- a/packages/aiCore/src/core/providers/schemas.ts
+++ b/packages/aiCore/src/core/providers/schemas.ts
@@ -7,6 +7,7 @@ import { createAzure } from '@ai-sdk/azure'
 import { type AzureOpenAIProviderSettings } from '@ai-sdk/azure'
 import { createDeepSeek } from '@ai-sdk/deepseek'
 import { createGoogleGenerativeAI } from '@ai-sdk/google'
+import { createHuggingFace } from '@ai-sdk/huggingface'
 import { createOpenAI, type OpenAIProviderSettings } from '@ai-sdk/openai'
 import { createOpenAICompatible } from '@ai-sdk/openai-compatible'
 import { LanguageModelV2 } from '@ai-sdk/provider'
@@ -28,7 +29,8 @@ export const baseProviderIds = [
   'azure',
   'azure-responses',
   'deepseek',
-  'openrouter'
+  'openrouter',
+  'huggingface'
 ] as const
 
 /**
@@ -132,6 +134,12 @@ export const baseProviders = [
     name: 'OpenRouter',
     creator: createOpenRouter,
     supportsImageGeneration: true
+  },
+  {
+    id: 'huggingface',
+    name: 'HuggingFace',
+    creator: createHuggingFace,
+    supportsImageGeneration: true
   }
 ] as const satisfies BaseProvider[]
 
diff --git a/src/renderer/src/aiCore/plugins/telemetryPlugin.ts b/src/renderer/src/aiCore/plugins/telemetryPlugin.ts
index 75bf6e116c..0f06091c5a 100644
--- a/src/renderer/src/aiCore/plugins/telemetryPlugin.ts
+++ b/src/renderer/src/aiCore/plugins/telemetryPlugin.ts
@@ -49,7 +49,7 @@ class AdapterTracer {
       this.cachedParentContext = undefined
     }
 
-    logger.info('AdapterTracer created with parent context info', {
+    logger.debug('AdapterTracer created with parent context info', {
       topicId,
       modelName,
       parentTraceId: this.parentSpanContext?.traceId,
@@ -62,7 +62,7 @@ class AdapterTracer {
   startActiveSpan<F extends (span: Span) => any>(name: string, options: any, fn: F): ReturnType<F>
   startActiveSpan<F extends (span: Span) => any>(name: string, options: any, context: any, fn: F): ReturnType<F>
   startActiveSpan<F extends (span: Span) => any>(name: string, arg2?: any, arg3?: any, arg4?: any): ReturnType<F> {
-    logger.info('AdapterTracer.startActiveSpan called', {
+    logger.debug('AdapterTracer.startActiveSpan called', {
       spanName: name,
       topicId: this.topicId,
       modelName: this.modelName,
@@ -88,7 +88,7 @@ class AdapterTracer {
         // 包装span的end方法
         const originalEnd = span.end.bind(span)
         span.end = (endTime?: any) => {
-          logger.info('AI SDK span.end() called in startActiveSpan - about to convert span', {
+          logger.debug('AI SDK span.end() called in startActiveSpan - about to convert span', {
             spanName: name,
             spanId: span.spanContext().spanId,
             traceId: span.spanContext().traceId,
@@ -101,14 +101,14 @@ class AdapterTracer {
 
           // 转换并保存 span 数据
           try {
-            logger.info('Converting AI SDK span to SpanEntity (from startActiveSpan)', {
+            logger.debug('Converting AI SDK span to SpanEntity (from startActiveSpan)', {
               spanName: name,
               spanId: span.spanContext().spanId,
               traceId: span.spanContext().traceId,
               topicId: this.topicId,
               modelName: this.modelName
             })
-            logger.info('span', span)
+            logger.silly('span', span)
             const spanEntity = AiSdkSpanAdapter.convertToSpanEntity({
               span,
               topicId: this.topicId,
@@ -118,7 +118,7 @@ class AdapterTracer {
             // 保存转换后的数据
             window.api.trace.saveEntity(spanEntity)
 
-            logger.info('AI SDK span converted and saved successfully (from startActiveSpan)', {
+            logger.debug('AI SDK span converted and saved successfully (from startActiveSpan)', {
               spanName: name,
               spanId: span.spanContext().spanId,
               traceId: span.spanContext().traceId,
@@ -151,7 +151,7 @@ class AdapterTracer {
       if (this.parentSpanContext) {
         try {
           const ctx = trace.setSpanContext(otelContext.active(), this.parentSpanContext)
-          logger.info('Created active context with parent SpanContext for startActiveSpan', {
+          logger.debug('Created active context with parent SpanContext for startActiveSpan', {
             spanName: name,
             parentTraceId: this.parentSpanContext.traceId,
             parentSpanId: this.parentSpanContext.spanId,
@@ -218,7 +218,7 @@ export function createTelemetryPlugin(config: TelemetryPluginConfig) {
       if (effectiveTopicId) {
         try {
           // 从 SpanManagerService 获取当前的 span
-          logger.info('Attempting to find parent span', {
+          logger.debug('Attempting to find parent span', {
             topicId: effectiveTopicId,
             requestId: context.requestId,
             modelName: modelName,
@@ -230,7 +230,7 @@ export function createTelemetryPlugin(config: TelemetryPluginConfig) {
           if (parentSpan) {
             // 直接使用父 span 的 SpanContext，避免手动拼装字段遗漏
             parentSpanContext = parentSpan.spanContext()
-            logger.info('Found active parent span for AI SDK', {
+            logger.debug('Found active parent span for AI SDK', {
               parentSpanId: parentSpanContext.spanId,
               parentTraceId: parentSpanContext.traceId,
               topicId: effectiveTopicId,
@@ -302,7 +302,7 @@ export function createTelemetryPlugin(config: TelemetryPluginConfig) {
             logger.debug('Updated active context with parent span')
           })
 
-          logger.info('Set parent context for AI SDK spans', {
+          logger.debug('Set parent context for AI SDK spans', {
             parentSpanId: parentSpanContext?.spanId,
             parentTraceId: parentSpanContext?.traceId,
             hasActiveContext: !!activeContext,
@@ -313,7 +313,7 @@ export function createTelemetryPlugin(config: TelemetryPluginConfig) {
         }
       }
 
-      logger.info('Injecting AI SDK telemetry config with adapter', {
+      logger.debug('Injecting AI SDK telemetry config with adapter', {
         requestId: context.requestId,
         topicId: effectiveTopicId,
         modelId: context.modelId,
diff --git a/src/renderer/src/aiCore/provider/providerInitialization.ts b/src/renderer/src/aiCore/provider/providerInitialization.ts
index 9942ffa405..665f2bd05c 100644
--- a/src/renderer/src/aiCore/provider/providerInitialization.ts
+++ b/src/renderer/src/aiCore/provider/providerInitialization.ts
@@ -63,6 +63,14 @@ export const NEW_PROVIDER_CONFIGS: ProviderConfig[] = [
     creatorFunctionName: 'createMistral',
     supportsImageGeneration: false,
     aliases: ['mistral']
+  },
+  {
+    id: 'huggingface',
+    name: 'HuggingFace',
+    import: () => import('@ai-sdk/huggingface'),
+    creatorFunctionName: 'createHuggingFace',
+    supportsImageGeneration: true,
+    aliases: ['hf', 'hugging-face']
   }
 ] as const
 
diff --git a/src/renderer/src/aiCore/utils/options.ts b/src/renderer/src/aiCore/utils/options.ts
index d151b57029..087a9ef157 100644
--- a/src/renderer/src/aiCore/utils/options.ts
+++ b/src/renderer/src/aiCore/utils/options.ts
@@ -90,7 +90,9 @@ export function buildProviderOptions(
           serviceTier: serviceTierSetting
         }
         break
-
+      case 'huggingface':
+        providerSpecificOptions = buildOpenAIProviderOptions(assistant, model, capabilities)
+        break
       case 'anthropic':
         providerSpecificOptions = buildAnthropicProviderOptions(assistant, model, capabilities)
         break
diff --git a/src/renderer/src/aiCore/utils/reasoning.ts b/src/renderer/src/aiCore/utils/reasoning.ts
index 6e57074980..86a762897f 100644
--- a/src/renderer/src/aiCore/utils/reasoning.ts
+++ b/src/renderer/src/aiCore/utils/reasoning.ts
@@ -10,6 +10,7 @@ import {
   isGrok4FastReasoningModel,
   isGrokReasoningModel,
   isOpenAIDeepResearchModel,
+  isOpenAIModel,
   isOpenAIReasoningModel,
   isQwenAlwaysThinkModel,
   isQwenReasoningModel,
@@ -319,6 +320,20 @@ export function getOpenAIReasoningParams(assistant: Assistant, model: Model): Re
   if (!isReasoningModel(model)) {
     return {}
   }
+
+  let reasoningEffort = assistant?.settings?.reasoning_effort
+
+  if (!reasoningEffort) {
+    return {}
+  }
+
+  // 非OpenAI模型，但是Provider类型是responses/azure openai的情况
+  if (!isOpenAIModel(model)) {
+    return {
+      reasoningEffort
+    }
+  }
+
   const openAI = getStoreSetting('openAI') as SettingsState['openAI']
   const summaryText = openAI?.summaryText || 'off'
 
@@ -330,16 +345,10 @@ export function getOpenAIReasoningParams(assistant: Assistant, model: Model): Re
     reasoningSummary = summaryText
   }
 
-  let reasoningEffort = assistant?.settings?.reasoning_effort
-
   if (isOpenAIDeepResearchModel(model)) {
     reasoningEffort = 'medium'
   }
 
-  if (!reasoningEffort) {
-    return {}
-  }
-
   // OpenAI 推理参数
   if (isSupportedReasoningEffortOpenAIModel(model)) {
     return {
diff --git a/src/renderer/src/assets/images/providers/huggingface.webp b/src/renderer/src/assets/images/providers/huggingface.webp
new file mode 100644
index 0000000000..72413f893e
Binary files /dev/null and b/src/renderer/src/assets/images/providers/huggingface.webp differ
diff --git a/src/renderer/src/config/models/default.ts b/src/renderer/src/config/models/default.ts
index c3a40e6ef7..f3e63e631d 100644
--- a/src/renderer/src/config/models/default.ts
+++ b/src/renderer/src/config/models/default.ts
@@ -1837,5 +1837,6 @@ export const SYSTEM_MODELS: Record<SystemProviderId | 'defaultModel', Model[]> =
       provider: 'longcat',
       group: 'LongCat'
     }
-  ]
+  ],
+  huggingface: []
 }
diff --git a/src/renderer/src/config/providers.ts b/src/renderer/src/config/providers.ts
index 7f8d95dcd1..0008013af4 100644
--- a/src/renderer/src/config/providers.ts
+++ b/src/renderer/src/config/providers.ts
@@ -22,6 +22,7 @@ import GoogleProviderLogo from '@renderer/assets/images/providers/google.png'
 import GPUStackProviderLogo from '@renderer/assets/images/providers/gpustack.svg'
 import GrokProviderLogo from '@renderer/assets/images/providers/grok.png'
 import GroqProviderLogo from '@renderer/assets/images/providers/groq.png'
+import HuggingfaceProviderLogo from '@renderer/assets/images/providers/huggingface.webp'
 import HyperbolicProviderLogo from '@renderer/assets/images/providers/hyperbolic.png'
 import InfiniProviderLogo from '@renderer/assets/images/providers/infini.png'
 import IntelOvmsLogo from '@renderer/assets/images/providers/intel.png'
@@ -653,6 +654,16 @@ export const SYSTEM_PROVIDERS_CONFIG: Record<SystemProviderId, SystemProvider> =
     models: SYSTEM_MODELS.longcat,
     isSystem: true,
     enabled: false
+  },
+  huggingface: {
+    id: 'huggingface',
+    name: 'Hugging Face',
+    type: 'openai-response',
+    apiKey: '',
+    apiHost: 'https://router.huggingface.co/v1/',
+    models: [],
+    isSystem: true,
+    enabled: false
   }
 } as const
 
@@ -717,7 +728,8 @@ export const PROVIDER_LOGO_MAP: AtLeast<SystemProviderId, string> = {
   'aws-bedrock': AwsProviderLogo,
   poe: 'poe', // use svg icon component
   aionly: AiOnlyProviderLogo,
-  longcat: LongCatProviderLogo
+  longcat: LongCatProviderLogo,
+  huggingface: HuggingfaceProviderLogo
 } as const
 
 export function getProviderLogo(providerId: string) {
@@ -1344,6 +1356,17 @@ export const PROVIDER_URLS: Record<SystemProviderId, ProviderUrls> = {
       docs: 'https://longcat.chat/platform/docs/zh/',
       models: 'https://longcat.chat/platform/docs/zh/APIDocs.html'
     }
+  },
+  huggingface: {
+    api: {
+      url: 'https://router.huggingface.co/v1/'
+    },
+    websites: {
+      official: 'https://huggingface.co/',
+      apiKey: 'https://huggingface.co/settings/tokens',
+      docs: 'https://huggingface.co/docs',
+      models: 'https://huggingface.co/models'
+    }
   }
 }
 
diff --git a/src/renderer/src/i18n/label.ts b/src/renderer/src/i18n/label.ts
index 51edc964b6..e679200804 100644
--- a/src/renderer/src/i18n/label.ts
+++ b/src/renderer/src/i18n/label.ts
@@ -88,7 +88,9 @@ const providerKeyMap = {
   zhinao: 'provider.zhinao',
   zhipu: 'provider.zhipu',
   poe: 'provider.poe',
-  aionly: 'provider.aionly'
+  aionly: 'provider.aionly',
+  longcat: 'provider.longcat',
+  huggingface: 'provider.huggingface'
 } as const
 
 /**
diff --git a/src/renderer/src/i18n/locales/en-us.json b/src/renderer/src/i18n/locales/en-us.json
index ab3bedef6a..a5a93e4356 100644
--- a/src/renderer/src/i18n/locales/en-us.json
+++ b/src/renderer/src/i18n/locales/en-us.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Grok",
     "groq": "Groq",
+    "huggingface": "Hugging Face",
     "hunyuan": "Tencent Hunyuan",
     "hyperbolic": "Hyperbolic",
     "infini": "Infini",
     "jina": "Jina",
     "lanyun": "LANYUN",
     "lmstudio": "LM Studio",
+    "longcat": "LongCat AI",
     "minimax": "MiniMax",
     "mistral": "Mistral",
     "modelscope": "ModelScope",
diff --git a/src/renderer/src/i18n/locales/zh-cn.json b/src/renderer/src/i18n/locales/zh-cn.json
index ed728ef2c3..44f051be07 100644
--- a/src/renderer/src/i18n/locales/zh-cn.json
+++ b/src/renderer/src/i18n/locales/zh-cn.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Grok",
     "groq": "Groq",
+    "huggingface": "Hugging Face",
     "hunyuan": "腾讯混元",
     "hyperbolic": "Hyperbolic",
     "infini": "无问芯穹",
     "jina": "Jina",
     "lanyun": "蓝耘科技",
     "lmstudio": "LM Studio",
+    "longcat": "龙猫",
     "minimax": "MiniMax",
     "mistral": "Mistral",
     "modelscope": "ModelScope 魔搭",
diff --git a/src/renderer/src/i18n/locales/zh-tw.json b/src/renderer/src/i18n/locales/zh-tw.json
index 89b51d5c1b..d933db01d5 100644
--- a/src/renderer/src/i18n/locales/zh-tw.json
+++ b/src/renderer/src/i18n/locales/zh-tw.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Grok",
     "groq": "Groq",
+    "huggingface": "Hugging Face",
     "hunyuan": "騰訊混元",
     "hyperbolic": "Hyperbolic",
     "infini": "無問芯穹",
     "jina": "Jina",
     "lanyun": "藍耘",
     "lmstudio": "LM Studio",
+    "longcat": "龍貓",
     "minimax": "MiniMax",
     "mistral": "Mistral",
     "modelscope": "ModelScope 魔搭",
diff --git a/src/renderer/src/i18n/translate/de-de.json b/src/renderer/src/i18n/translate/de-de.json
index 3d9de52588..3a44387d5d 100644
--- a/src/renderer/src/i18n/translate/de-de.json
+++ b/src/renderer/src/i18n/translate/de-de.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Grok",
     "groq": "Groq",
+    "huggingface": "Hugging Face",
     "hunyuan": "Tencent Hunyuan",
     "hyperbolic": "Hyperbolic",
     "infini": "Infini-AI",
     "jina": "Jina",
     "lanyun": "Lanyun Technologie",
     "lmstudio": "LM Studio",
+    "longcat": "Meißner Riesenhamster",
     "minimax": "MiniMax",
     "mistral": "Mistral",
     "modelscope": "ModelScope",
diff --git a/src/renderer/src/i18n/translate/el-gr.json b/src/renderer/src/i18n/translate/el-gr.json
index c740b1b106..59b25aea2d 100644
--- a/src/renderer/src/i18n/translate/el-gr.json
+++ b/src/renderer/src/i18n/translate/el-gr.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Grok",
     "groq": "Groq",
+    "huggingface": "Hugging Face",
     "hunyuan": "Tencent Hunyuan",
     "hyperbolic": "Υπερβολικός",
     "infini": "Χωρίς Ερώτημα Xin Qiong",
     "jina": "Jina",
     "lanyun": "Λανιούν Τεχνολογία",
     "lmstudio": "LM Studio",
+    "longcat": "Τσίρο",
     "minimax": "MiniMax",
     "mistral": "Mistral",
     "modelscope": "ModelScope Magpie",
diff --git a/src/renderer/src/i18n/translate/es-es.json b/src/renderer/src/i18n/translate/es-es.json
index 654510415e..70defe51da 100644
--- a/src/renderer/src/i18n/translate/es-es.json
+++ b/src/renderer/src/i18n/translate/es-es.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Grok",
     "groq": "Groq",
+    "huggingface": "Hugging Face",
     "hunyuan": "Tencent Hùnyuán",
     "hyperbolic": "Hiperbólico",
     "infini": "Infini",
     "jina": "Jina",
     "lanyun": "Tecnología Lanyun",
     "lmstudio": "Estudio LM",
+    "longcat": "Totoro",
     "minimax": "Minimax",
     "mistral": "Mistral",
     "modelscope": "ModelScope Módulo",
diff --git a/src/renderer/src/i18n/translate/fr-fr.json b/src/renderer/src/i18n/translate/fr-fr.json
index 65b7bd6d12..305378447e 100644
--- a/src/renderer/src/i18n/translate/fr-fr.json
+++ b/src/renderer/src/i18n/translate/fr-fr.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Grok",
     "groq": "Groq",
+    "huggingface": "Hugging Face",
     "hunyuan": "Tencent HunYuan",
     "hyperbolic": "Hyperbolique",
     "infini": "Sans Frontières Céleste",
     "jina": "Jina",
     "lanyun": "Technologie Lan Yun",
     "lmstudio": "Studio LM",
+    "longcat": "Mon voisin Totoro",
     "minimax": "MiniMax",
     "mistral": "Mistral",
     "modelscope": "ModelScope MoDa",
diff --git a/src/renderer/src/i18n/translate/ja-jp.json b/src/renderer/src/i18n/translate/ja-jp.json
index 1ee2139df7..6e66ace09f 100644
--- a/src/renderer/src/i18n/translate/ja-jp.json
+++ b/src/renderer/src/i18n/translate/ja-jp.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Grok",
     "groq": "Groq",
+    "huggingface": "ハギングフェイス",
     "hunyuan": "腾讯混元",
     "hyperbolic": "Hyperbolic",
     "infini": "Infini",
     "jina": "Jina",
     "lanyun": "LANYUN",
     "lmstudio": "LM Studio",
+    "longcat": "トトロ",
     "minimax": "MiniMax",
     "mistral": "Mistral",
     "modelscope": "ModelScope",
diff --git a/src/renderer/src/i18n/translate/pt-pt.json b/src/renderer/src/i18n/translate/pt-pt.json
index e5231a07e9..4a6dc5b2b6 100644
--- a/src/renderer/src/i18n/translate/pt-pt.json
+++ b/src/renderer/src/i18n/translate/pt-pt.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Compreender",
     "groq": "Groq",
+    "huggingface": "Hugging Face",
     "hunyuan": "Tencent Hún Yuán",
     "hyperbolic": "Hiperbólico",
     "infini": "Infinito",
     "jina": "Jina",
     "lanyun": "Lanyun Tecnologia",
     "lmstudio": "Estúdio LM",
+    "longcat": "Totoro",
     "minimax": "Minimax",
     "mistral": "Mistral",
     "modelscope": "ModelScope MôDá",
diff --git a/src/renderer/src/i18n/translate/ru-ru.json b/src/renderer/src/i18n/translate/ru-ru.json
index 59df9b25f7..477fcb0a28 100644
--- a/src/renderer/src/i18n/translate/ru-ru.json
+++ b/src/renderer/src/i18n/translate/ru-ru.json
@@ -2345,12 +2345,14 @@
     "gpustack": "GPUStack",
     "grok": "Grok",
     "groq": "Groq",
+    "huggingface": "Hugging Face",
     "hunyuan": "Tencent Hunyuan",
     "hyperbolic": "Hyperbolic",
     "infini": "Infini",
     "jina": "Jina",
     "lanyun": "LANYUN",
     "lmstudio": "LM Studio",
+    "longcat": "Тоторо",
     "minimax": "MiniMax",
     "mistral": "Mistral",
     "modelscope": "ModelScope",
diff --git a/src/renderer/src/store/index.ts b/src/renderer/src/store/index.ts
index c9ec0d5e81..85afd68cb9 100644
--- a/src/renderer/src/store/index.ts
+++ b/src/renderer/src/store/index.ts
@@ -65,7 +65,7 @@ const persistedReducer = persistReducer(
   {
     key: 'cherry-studio',
     storage,
-    version: 166,
+    version: 167,
     blacklist: ['runtime', 'messages', 'messageBlocks', 'tabs'],
     migrate
   },
diff --git a/src/renderer/src/store/migrate.ts b/src/renderer/src/store/migrate.ts
index b0b4e36a81..7b7a834838 100644
--- a/src/renderer/src/store/migrate.ts
+++ b/src/renderer/src/store/migrate.ts
@@ -2720,6 +2720,15 @@ const migrateConfig = {
       logger.error('migrate 166 error', error as Error)
       return state
     }
+  },
+  '167': (state: RootState) => {
+    try {
+      addProvider(state, 'huggingface')
+      return state
+    } catch (error) {
+      logger.error('migrate 167 error', error as Error)
+      return state
+    }
   }
 }
 
diff --git a/src/renderer/src/types/provider.ts b/src/renderer/src/types/provider.ts
index 782d8e98fd..95461d14e9 100644
--- a/src/renderer/src/types/provider.ts
+++ b/src/renderer/src/types/provider.ts
@@ -162,7 +162,8 @@ export const SystemProviderIds = {
   'aws-bedrock': 'aws-bedrock',
   poe: 'poe',
   aionly: 'aionly',
-  longcat: 'longcat'
+  longcat: 'longcat',
+  huggingface: 'huggingface'
 } as const
 
 export type SystemProviderId = keyof typeof SystemProviderIds
diff --git a/yarn.lock b/yarn.lock
index 79909f1781..432a846a47 100644
--- a/yarn.lock
+++ b/yarn.lock
@@ -180,6 +180,32 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@ai-sdk/huggingface@npm:0.0.4":
+  version: 0.0.4
+  resolution: "@ai-sdk/huggingface@npm:0.0.4"
+  dependencies:
+    "@ai-sdk/openai-compatible": "npm:1.0.22"
+    "@ai-sdk/provider": "npm:2.0.0"
+    "@ai-sdk/provider-utils": "npm:3.0.12"
+  peerDependencies:
+    zod: ^3.25.76 || ^4
+  checksum: 10c0/756b8f820b89bf9550c9281dfe2a1a813477dec82be5557e236e8b5eaaf0204b65a65925ad486b7576c687f33c709f6d99fd4fc87a46b1add210435b08834986
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/huggingface@patch:@ai-sdk/huggingface@npm%3A0.0.4#~/.yarn/patches/@ai-sdk-huggingface-npm-0.0.4-8080836bc1.patch":
+  version: 0.0.4
+  resolution: "@ai-sdk/huggingface@patch:@ai-sdk/huggingface@npm%3A0.0.4#~/.yarn/patches/@ai-sdk-huggingface-npm-0.0.4-8080836bc1.patch::version=0.0.4&hash=ceb48e"
+  dependencies:
+    "@ai-sdk/openai-compatible": "npm:1.0.22"
+    "@ai-sdk/provider": "npm:2.0.0"
+    "@ai-sdk/provider-utils": "npm:3.0.12"
+  peerDependencies:
+    zod: ^3.25.76 || ^4
+  checksum: 10c0/4726a10de7a6fd554b58d62f79cd6514c2cc5166052e035ba1517e224a310ddb355a5d2922ee8507fb8d928d6d5b2b102d3d221af5a44b181e436e6b64382087
+  languageName: node
+  linkType: hard
+
 "@ai-sdk/mistral@npm:^2.0.19":
   version: 2.0.19
   resolution: "@ai-sdk/mistral@npm:2.0.19"
@@ -13853,6 +13879,7 @@ __metadata:
     "@agentic/tavily": "npm:^7.3.3"
     "@ai-sdk/amazon-bedrock": "npm:^3.0.35"
     "@ai-sdk/google-vertex": "npm:^3.0.40"
+    "@ai-sdk/huggingface": "patch:@ai-sdk/huggingface@npm%3A0.0.4#~/.yarn/patches/@ai-sdk-huggingface-npm-0.0.4-8080836bc1.patch"
     "@ai-sdk/mistral": "npm:^2.0.19"
     "@ai-sdk/perplexity": "npm:^2.0.13"
     "@ant-design/v5-patch-for-react-19": "npm:^1.0.3"