et0dev
/

Qwen3.5-122B-A10B-NVFP4-Full-GB10

Image-Text-to-Text

compressed-tensors

Mixture of Experts

8-bit precision

Model card Files Files and versions

Qwen3.5-122B-A10B-NVFP4-Full-GB10

70.8 GB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

demon-zombie

Add vLLM NVFP4 lm_head patch (ParallelLMHead -> ReplicatedLinear)

bacdce3 verified 3 months ago

vllm-patches
Add vLLM NVFP4 lm_head patch (ParallelLMHead -> ReplicatedLinear) 3 months ago
.gitattributes

1.64 kB
NVFP4-only quant v2 (all Linear incl MTP → NVFP4) 4 months ago
README.md

5.38 kB
Add model card (all-FP4 max-speed variant; quality note; serve + lm_head patch) 3 months ago
chat_template.jinja

7.76 kB
NVFP4-only quant v2 (all Linear incl MTP → NVFP4) 4 months ago
config.json

15 kB
Add ParallelLMHead to quantization targets for vLLM compat 4 months ago
generation_config.json

218 Bytes
NVFP4-only quant v2 (all Linear incl MTP → NVFP4) 4 months ago
model-00001-of-00002.safetensors

50 GB
xet

NVFP4-only quant v2 (all Linear incl MTP → NVFP4) 4 months ago
model-00002-of-00002.safetensors

20.8 GB
xet

NVFP4-only quant v2 (all Linear incl MTP → NVFP4) 4 months ago
model.safetensors.index.json

17.2 MB
xet

NVFP4-only quant v2 (all Linear incl MTP → NVFP4) 4 months ago
preprocessor_config.json

390 Bytes
Add preprocessor_config.json for vision support 4 months ago
recipe.yaml

1.25 kB
NVFP4-only quant v2 (all Linear incl MTP → NVFP4) 4 months ago
tokenizer.json

20 MB
xet

NVFP4-only quant v2 (all Linear incl MTP → NVFP4) 4 months ago
tokenizer_config.json

1.13 kB
NVFP4-only quant v2 (all Linear incl MTP → NVFP4) 4 months ago