Inference Providers
Active filters: 3-bit
unsloth/gemma-4-26b-a4b-it-UD-MLX-3bit
Image-Text-to-Text
• 25B • Updated • 192
• 6
NapYang/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-text-oQ3.5
Text Generation
• 27B • Updated • 2.6k
• 5
unsloth/gemma-4-31b-it-UD-MLX-3bit
Image-Text-to-Text
• 31B • Updated • 88
• 5
Brooooooklyn/Qwen3.5-27B-unsloth-mlx
Text Generation
• 6B • Updated • 4.88k
• 17
NapYang/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-text-oQ3.5
5B • Updated • 756
• 2
RepublicOfKorokke/gemma-4-26B-A4B-it-oQ3
4B • Updated • 970
• 2
kyr0/Gemma-4-Waldwicht-Sproessling
Text Generation
• 0.8B • Updated • 2
MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF
Text Generation
• 7B • Updated • 111k
• 135
adam-fleet/Qwen3-Next-80B-A3B-Instruct-REAM-mlx-3bit
Text Generation
• 60B • Updated • 198
• 1
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q3_K_XL-mlx
Text Generation
• 6B • Updated • 445
• 2
0xSero/glm-5-381-reap-w3a16
Text Generation
• 41B • Updated • 242
• 1
kyr0/Gemma-4-Waldwicht-Winzling
Text Generation
• 0.7B • Updated • 1
kyr0/Gemma-4-Waldwicht-Juengling
Text Generation
• 1.0B • Updated • 1
kaitchup/Llama-2-7b-gptq-3bit
Text Generation
• Updated • 18
clibrain/Llama-2-7b-ft-instruct-es-gptq-3bit
Text Generation
• Updated • 10
• 3
clibrain/Llama-2-13b-ft-instruct-es-gptq-3bit
Text Generation
• Updated • 5
• 3
MiNeves-tops/opt-125m-gptq-3bit
Text Generation
• Updated • 5
Text Generation
• Updated • 8
LoneStriker/Yi-6B-200K-3.0bpw-h6-exl2
Text Generation
• Updated • 4
danny0122/Llama-2-7b-hf-gptq-3bits
Text Generation
• 6B • Updated • 2
danny0122/Llama-2-7b-hf-gptq-3bitssafe
Text Generation
• 6B • Updated • 4
danny0122/stablelm-base-alpha-3b-gptq-3bits
Text Generation
• 3B • Updated • 4
danny0122/stablelm-base-alpha-3b-gptq-3bitssafe
Text Generation
• 3B • Updated • 4
SicariusSicariiStuff/Tenebra_PreAlpha_128g_3BIT
Text Generation
• 31B • Updated • 5
mahihossain666/llama-2-70b-hf-quantized-3bits-GPTQ
Text Generation
• 65B • Updated • 5
SicariusSicariiStuff/Tenebra_PreAlpha_No_Group_g_3BIT
Text Generation
• 31B • Updated • 8
kaitchup/Mistral-7B-v0.1-gptq-3bit
Text Generation
• 7B • Updated • 5
kaitchup/Llama-2-13b-hf-gptq-3bit
Text Generation
• 12B • Updated • 8
kaitchup/Llama-2-7b-hf-gptq-3bit
Text Generation
• 6B • Updated • 600
• 1
Text Generation
• 3B • Updated • 229
• 6