跳到主要内容

支持模型及平台

支持模型

模型分类模型
QwenQwen3-8B
Qwen3-14B
Qwen/Qwen2-7B
Qwen2.5-7B
Qwen2.5-72B-Instruct
Qwen3.5-27B
Qwen3.5-35B-A3B
Qwen3.5-397B-A17B
Qwen/Qwen3-30B-A3B
Qwen3-30B-A3B-GPTQ-Int4(GPTQ Int4 量化)
Qwen-OmniQwen3-Omni
Qwen/Qwen2.5-Omni-7B
Qwen3-Omni-30B-A3B-Instruct
Qwen-VLQwen3-VL
Qwen/Qwen2.5-VL-3B-Instruct
Qwen/Qwen2-VL-7B-Instruct
Qwen2.5-VL-7B-Instruct
Qwen2.5-VL-72B-Instruct
Qwen3-VL-8B-Instruct
Qwen3-VL-30B-A3B-Instruct
GLMchatglm2-6b
glm-4-9b-chat-hf
GLM-VGLM-4.6V-Flash
Mistral / Mixtralmistralai/Mistral-7B-v0.1
mistralai/Mixtral-8x7B-v0.1
FLM / LFMFLM-2-52B-Instruct-2407
LFM2-24B-A2B
Graniteibm-granite/granite-3.0-2b-base
OlmoOlmo-3-7B-Instruct
NanbeigeNanbeige4.1-3B4B
StepStep-3.5-Flash
GPTopenai-community/gpt2
BLIP-2Salesforce/blip2-opt-2.7b
LLaVAllava-hf/llava-1.5-7b-hf
SmolVLMSmolVLM2-2.2B-Instruct(需安装 num2words
Rerankercross-encoder/ms-marco-MiniLM-L6-v2
DeepSeekDeepSeek-R1-Distill-Llama-70B
DeepSeek-OCR
MambaMamba-Coderstral-7B
Mamba-Codestral-7B-v0.1
Embedding 模型BAAI/bge-base-en-v1.5
BAAI/bge-m3
Qwen/Qwen3-Embedding-0.6B
Qwen3-Embedding-8B
intfloat/e5-mistral-7b-instruct
语音识别模型openai/whisper-small(需安装 librosa
openai/whisper-large(需安装 librosa
whisper-large-v3(不要设置 --max-model-len
QwQQwQ-32B-Preview

平台支持

GPUCPUOSLinux kernel
MTT S4000IntelUbuntu22.04.x LTS5.15.0-105-generic