amd/Qwen3-8B-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 at 84077299d33364d5f047457a868ea44ba93b1b8b

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

7.8 GB

1 contributor

History: 3 commits

XuebinWang

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies

8407729 verified 3 months ago

.gitattributes

1.57 kB

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies 3 months ago
README.md

31 Bytes

initial commit 3 months ago
added_tokens.json

707 Bytes

Qwen3-8B Auto Mixed Precision (AMP) Quark quantized model at effective bits 4.9227 by xuebwang 3 months ago
chat_template.jinja

4.17 kB

Qwen3-8B Auto Mixed Precision (AMP) Quark quantized model at effective bits 4.9227 by xuebwang 3 months ago
config.json

424 kB

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies 3 months ago
generation_config.json

214 Bytes

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies 3 months ago
merges.txt

1.67 MB

Qwen3-8B Auto Mixed Precision (AMP) Quark quantized model at effective bits 4.9227 by xuebwang 3 months ago
model-00001-of-00002.safetensors

5 GB
xet

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies 3 months ago
model-00002-of-00002.safetensors

2.79 GB
xet

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies 3 months ago
model.safetensors.index.json

73.3 kB

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies 3 months ago
special_tokens_map.json

388 Bytes

Qwen3-8B Auto Mixed Precision (AMP) Quark quantized model at effective bits 4.9227 by xuebwang 3 months ago
tokenizer.json

11.4 MB
xet

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies 3 months ago
tokenizer_config.json

5.43 kB

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies 3 months ago
vocab.json

2.78 MB

update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies 3 months ago