Inference Providers
Active filters: sglang
Text-to-Speech
• Updated • 1.63k
• 15
bullpoint/Qwen3-Coder-Next-AWQ-4bit
Text Generation
• 14B • Updated • 454k
• 21
Image-Text-to-Text
• 3B • Updated • 1.92k
• 2
QuantTrio/Qwen3-Coder-Next-E336
Text Generation
• 53B • Updated • 10
• 2
AxionML/Qwen3.5-122B-A10B-NVFP4
Image-Text-to-Text
• 62B • Updated • 2.84k
• 5
AxionML/Qwen3.5-35B-A3B-NVFP4
Image-Text-to-Text
• Updated • 90k
• 3
Image-Text-to-Text
• 2B • Updated • 3.05k
• 1
Alexzander85/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-NVFP4-MLP-FP8KV
Text Generation
• 8B • Updated • 1.05k
• 4
surogate/Qwen3.5-4B-NVFP4
Image-Text-to-Text
• 3B • Updated • 2.92k
• 1
rhoninseiei/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-ModelOpt-NVFP4
Image-Text-to-Text
• 17B • Updated • 429
• 1
MickJ/Wan2.2-S2V-14B-overlay
Updated • 296
• 1
SurfaceData/llava-v1.6-mistral-7b-sglang
Image-Text-to-Text
• 8B • Updated • 14
• 9
SurfaceData/llava-v1.6-vicuna-7b-sglang
Image-Text-to-Text
• 7B • Updated • 17
• 1
tclf90/qwen2.5-72b-instruct-gptq-int4
Text Generation
• 73B • Updated • 116
• 2
tclf90/qwen2.5-72b-instruct-gptq-int3
Text Generation
• 69B • Updated • 115
alvarobartt/grok-2-tokenizer
Text Generation
• Updated • 43
• 4
VibeStudio/MiniMax-M2-THRIFT
173B • Updated • 1.75k
• 35
mradermacher/MiniMax-M2-THRIFT-GGUF
JasmineBBB/Kimi-Linear-48B-A3B-Instruct-bnb-4bit
Text Generation
• 49B • Updated • 5
• 1
mradermacher/MiniMax-M2-THRIFT-i1-GGUF
173B • Updated • 144
• 10
bartowski/VibeStudio_MiniMax-M2-THRIFT-GGUF
Text Generation
• 173B • Updated • 3.08k
• 8
VibeStudio/MiniMax-M2-THRIFT-55
106B • Updated • 165
• 5
JinnP/SGLang-EAGLE3-Qwen3-Coder-30B-A3B-Instruct
Text Generation
• 0.2B • Updated • 62
• 1
mradermacher/MiniMax-M2-THRIFT-55-GGUF
106B • Updated • 67
• 2
mradermacher/MiniMax-M2-THRIFT-55-i1-GGUF
106B • Updated • 495
• 2
VibeStudio/MiniMax-M2-THRIFT-55-MLX-4bit
106B • Updated • 103
• 2
VibeStudio/MiniMax-M2-THRIFT-55-MLX-6bit
106B • Updated • 47
Doradus-AI/MiroThinker-v1.0-30B-FP8
Text Generation
• 31B • Updated • 48
• 4
Doradus-AI/Hermes-4.3-36B-FP8
Text Generation
• 36B • Updated • 62
• 2