Inference Providers
Active filters: quark
empero-ai/Quark-150M-128K-Zero
Text Generation • 0.2B • Updated • 199
• 19
amd/Qwen3.8-27B-Quark-AWQ-MXFP4
Image-Text-to-Text • 16B • Updated • 39.7k
• 47
amd/Qwen3.8-Flash-Next-Quark-MXFP4
Image-Text-to-Text • 119B • Updated • 17k
• 8
flechin/Qwen3.8-27B-Randean-MXFP4
Image-Text-to-Text • 16B • Updated • 374
• 6
amd/Qwen3.8-27B-Quark-AWQ-INT4-W4A16
Image-Text-to-Text • 6B • Updated • 5.23k
• 24
magiccodingman/Qwen3.8-27B-MXFP4-MagicQuant-GGUF
Image-Text-to-Text • 27B • Updated • 7.05k
• 7
amd/GLM-5.3-Quark-MXFP4-AttnFP8
Text Generation • 384B • Updated • 4.47k
• 7
ukisai/Swift-1.5-Qwen3.8-27b-Quark-FP8-dynamic-AMD
Image-Text-to-Text • 28B • Updated • 227
• 5
amd/Mistral-Large-4-1T-A52B-Quark-MXFP4
Updated • 2.78k
• 2
amd/Qwen3.8-Flash-Next-Quark-TokenPLE-AWQ-UINT4
Text Generation • 21B • Updated • 194
• 1
empero-ai/Quark-150M-128K-Base
Text Generation • 0.2B • Updated • 70
• 1
fxmarty/llama-tiny-testing-quark-indev
1.03M • Updated • 10
fxmarty/llama-tiny-int4-per-group-sym
1.03M • Updated • 9
fxmarty/llama-tiny-w-fp8-a-fp8
1.03M • Updated • 10
fxmarty/llama-tiny-w-fp8-a-fp8-o-fp8
1.03M • Updated • 12
fxmarty/llama-tiny-w-int8-per-tensor
1.03M • Updated • 10
fxmarty/llama-small-int4-per-group-sym-awq
16.7M • Updated • 6
fxmarty/quark-legacy-int8
1.03M • Updated • 10
fxmarty/llama-tiny-w-int8-b-int8-per-tensor
1.03M • Updated • 17
fxmarty/llama-small-int4-per-group-sym-awq-old
16.7M • Updated • 7
amd-quark/llama-tiny-w-int8-per-tensor
1.03M • Updated • 22
amd-quark/llama-tiny-w-int8-b-int8-per-tensor
1.03M • Updated • 14
amd-quark/llama-tiny-w-fp8-a-fp8
1.03M • Updated • 23
amd-quark/llama-tiny-w-fp8-a-fp8-o-fp8
1.03M • Updated • 28
amd-quark/llama-tiny-int4-per-group-sym
1.03M • Updated • 18
amd-quark/llama-small-int4-per-group-sym-awq
16.7M • Updated • 39
amd-quark/quark-legacy-int8
1.03M • Updated • 5
amd/Llama-3.1-8B-Instruct-FP8-KV-Quark-test
8B • Updated • 628
amd/Llama-3.1-8B-Instruct-w-int8-a-int8-sym-test
8B • Updated • 573
EmbeddedLLM/Llama-3.1-8B-Instruct-w_fp8_per_channel_sym
Text Generation • 8B • Updated • 16