Models

matmelis/Llama_3.2_1B_w_uint4_autosmoothquant_gptq

0.4B • Updated Aug 1 • 4

matmelis/Llama_3.2_1B_w_uint4_qronos

0.4B • Updated Aug 7 • 1

matmelis/Llama_3.2_3B_w_mxfp4_a_mxfp4_qronos

2B • Updated Aug 7 • 1

EliovpAI/Qwen3-0.6B-FP8-KV

Text Generation • 0.6B • Updated Aug 2 • 4

matmelis/Llama_3.2_3B_w_mxfp4_a_mxfp4_gptq

2B • Updated Aug 6 • 1

matmelis/Llama_3.2_1B_w_int3_qronos

0.6B • Updated Aug 12 • 1

matmelis/Llama_3.2_3B_w_uint4_qronos

0.8B • Updated Aug 7 • 4

matmelis/Llama_3.2_3B_w_int3_qronos

1B • Updated Aug 12 • 1

matmelis/Llama_3.2_3B_w_int2_gptq

3B • Updated Aug 7 • 2

matmelis/Llama_3.2_3B_w_int3_gptq

3B • Updated Aug 7

matmelis/Llama_3.2_3B_w_int2_qronos

3B • Updated Aug 7 • 1

matmelis/Llama_3.2_1B_w_int3_gptq

0.6B • Updated Aug 11 • 1

matmelis/Llama_3.2_3B_w_uint4_gptq

0.8B • Updated Aug 7 • 2

matmelis/Llama_3.2_1B_w_int2_qronos

1B • Updated Aug 7 • 1

matmelis/Llama_3.2_1B_w_int2_gptq

1B • Updated Aug 7 • 1

matmelis/Llama_3.2_1B_w_uint4_smoothquant_qronos

0.4B • Updated Aug 7 • 1

haoyang-amd/output_oss_120b_moe_w_mxfp4_a_mxfp4

174B • Updated Aug 19 • 1

haoyang-amd/output_oss_20b_moe_w_mxfp4_a_bfloat16

11B • Updated Aug 20 • 1

matmelis/Llama_3.2_1B_w_mxfp4_a_mxfp4_gptq

0.8B • Updated Aug 20 • 1

matmelis/Llama_3.2_1B_w_mxfp4_a_mxfp4_qronos

0.8B • Updated Aug 20 • 1

amd/Mixtral-8x7B-Instruct-v0.1-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

37B • Updated 9 days ago • 60

amd/Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

55B • Updated Sep 26 • 3

Keozon/GLM-4.5-Air-fp8_e4m3-quark-gfx1100

107B • Updated Sep 1 • 2 • 1

amd/Qwen3-8B-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

6B • Updated Sep 26 • 25 • 2

amd/Qwen2.5-1.5B-Instruct-ptpc-Quark-ts

2B • Updated Sep 11 • 1.5k

EmbeddedLLM/Qwen3-Coder-480B-A35B-Instruct-FP8-Dynamic

480B • Updated Sep 13 • 269

Quark-NPU-Workshop/Phi-3-mini-4k-instruct

0.6B • Updated Oct 7 • 5

Quark-NPU-Workshop/Hermes-3-Llama-3.2-3B-awq-g128-int4-asym-bf16-onnx-hybrid

0.8B • Updated Oct 8 • 4

Quark-NPU-Workshop/po-phi3-mini-4k-ins

0.6B • Updated Oct 8 • 4

playable/playable1-int4-bfloat16

1B • Updated 29 days ago • 25