Inference Providers
Active filters: awq
QuantTrio/Qwen3.6-35B-A3B-AWQ
Image-Text-to-Text
• 36B • Updated • 760k
• 28
QuantTrio/Qwen3.6-27B-AWQ-6Bit
Image-Text-to-Text
• 28B • Updated • 56.8k
• 15
sanskar003/Qwen3.5-4B-AWQ
Image-Text-to-Text
• 5B • Updated • 31
• 2
hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4
Text Generation
• Updated • 295k
• 110
Orion-zhen/aya-expanse-32b-AWQ
Text Generation
• 34B • Updated • 185
• 6
LGAI-EXAONE/EXAONE-Deep-32B-AWQ
Text Generation
• 32B • Updated • 120
• 21
Text Generation
• 15B • Updated • 1.79M
• 71
Text Generation
• 8B • Updated • 385k
• 51
Text Generation
• 4B • Updated • 539k
• 30
alonsoko/gemma-4-31b-it-abliterated-heretic-AWQ-W4A16
Image-Text-to-Text
• 32B • Updated • 10.7k
• 13
cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit
Image-Text-to-Text
• 36B • Updated • 1.87M
• 82
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx
Text Generation
• 10B • Updated • 657
• 8
QuantTrio/Qwen3.6-27B-AWQ
Image-Text-to-Text
• 28B • Updated • 1.44M
• 19
shawnw3i/Huihui-Qwen3.6-27B-abliterated-AWQ-MTP
Image-Text-to-Text
• 6B • Updated • 65.1k
• 10
drawais/Granite-4.1-30B-NVFP4
Text Generation
• 16B • Updated • 337
• 1
mattbucci/gemma-4-12B-AWQ
Image-Text-to-Text
• 12B • Updated • 21.1k
• 2
spectator2026/MiniMax-M3-AWQ-int4
Image-Text-to-Text
• 69B • Updated • 537
• 1
sakamakismile/Krea-2-Turbo-NVFP4-AWQ
Text-to-Image
• Updated • 199
• 4
BatuhanECB/vibethinker-3b-finance-sft-quantized-v1
Text Generation
• 3B • Updated • 35
• 1
Cadododoom/Agents-A1-TextOnly-AWQ-INT4
36B • Updated • 1
Alennnndy/Qwen3.6-27B-AWQ-4bit
Text Generation
• 28B • Updated • 71
• 2
casperhansen/mpt-7b-8k-chat-awq
Text Generation
• Updated • 15
• 3
casperhansen/falcon-7b-awq
Text Generation
• Updated • 50
• 1
casperhansen/vicuna-7b-v1.5-awq
Text Generation
• Updated • 15
• 3
casperhansen/vicuna-7b-v1.5-awq-gemv
Text Generation
• Updated • 12
• 1
casperhansen/mpt-7b-8k-chat-awq-gemv
Text Generation
• Updated • 13
casperhansen/opt-125m-awq
Text Generation
• 0.2B • Updated • 143
• 3
casperhansen/tinyllama-1b-awq
Text Generation
• Updated • 33
• 1
Bomml/Llama-2-70B-chat-w4-g128-awq
Text Generation
• Updated TheBloke/Llama-2-7B-Chat-AWQ
Text Generation
• 7B • Updated • 1.95k
• 24