Inference Providers
Active filters: mlx-lm
HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning-MLX-4bit
Image-Text-to-Text
• 27B • Updated • 926
• 1
kacperbb/phi-3.5-mlx-finetuned
Updated • 11
fourbic/disarm-ew-llama3-finetuned
Text Generation
• 8B • Updated • 2
alexander-model/gpt_model_safe
Text Generation
• 21B • Updated • 15
halley-ai/gpt-oss-120b-MLX-8bit-gs32
Text Generation
• 117B • Updated • 102
• 1
halley-ai/gpt-oss-120b-MLX-bf16
Text Generation
• 117B • Updated • 386
• 3
halley-ai/gpt-oss-120b-MLX-6bit-gs64
Text Generation
• 117B • Updated • 122
• 1
LibraxisAI/Qwen3-Next-80B-A3B-Instruct-MLX-MXFP4
Text Generation
• 80B • Updated • 34
• 2
halley-ai/Qwen3-Next-80B-A3B-Instruct-MLX-4bit-gs64
Text Generation
• 80B • Updated • 17
• 1
halley-ai/Qwen3-Next-80B-A3B-Instruct-MLX-5bit-gs32
Text Generation
• 80B • Updated • 18
• 1
halley-ai/Qwen3-Next-80B-A3B-Instruct-MLX-6bit-gs64
Text Generation
• 80B • Updated • 9
• 1
Miemczyk/CharityPurposeAnalyser
Text Generation
• Updated ProbioticFarmer/toucan-qwen3-8b-lora
Text Generation
• Updated Text Generation
• Updated pherber3/Qwen3-Omni-30B-A3B-Instruct-4bit-mlx
31B • Updated • 788
• 8
Daizee/Gemma3-Callous-Calla-4B-mlx
Text Generation
• Updated • 14
Daizee/Dirty-Calla-4B-mlx
Text Generation
• Updated • 44
meetmerchant/tech-tweet-generator-llama3
Updated
codewithdark/Llama-3.2-3B-4bit-mlx
Text Generation
• 3B • Updated • 63
QuantLLM/Llama-3.2-3B-4bit-mlx
Text Generation
• 3B • Updated • 16
QuantLLM/Llama-3.2-3B-2bit-mlx
Text Generation
• 3B • Updated • 28
QuantLLM/Llama-3.2-3B-8bit-mlx
Text Generation
• 3B • Updated • 33
QuantLLM/Llama-3.2-3B-5bit-mlx
Text Generation
• 3B • Updated • 13
QuantLLM/functiongemma-270m-it-4bit-mlx
Text Generation
• 0.3B • Updated • 10
bisonnetworking/MediPhi-Instruct-mlx-4bit
Text Generation
• 0.6B • Updated • 29
mlx-community/Youtu-LLM-2B
Text Generation
• 2B • Updated • 8
mlx-community/Youtu-LLM-2B-4bit
Text Generation
• 0.3B • Updated • 104
• 4
felixmanojh/DJ-AI-Radio-MLX
Text Generation
• 77.3M • Updated • 2
Text Generation
• Updated • 699
• 185
petergilani/Qwen3-Coder-Next-8bit-g128
Text Generation
• 80B • Updated • 1.4k
• 1