Intel
/

Qwen3.5-397B-A17B-int4-AutoRound

4-bit precision

Model card Files Files and versions

Resources

View closed (0)

model.language_model.layers.59.mlp.experts.213.down_proj.qweight is duplicated in shard 39 and 40

#5 opened 12 days ago by

Intel/Qwen3.5-397B-A17B-int4-AutoRound.guff wanted!

#4 opened 21 days ago by

MartinPatterson

Any chance we could get a tuned (non-RTN) version like with 122B model?

#3 opened 22 days ago by

sglang vllm?

#2 opened 22 days ago by

[ISSUE] W4A16 Kernel Selection Failure on Ampere A100 with TP > 1

#1 opened about 1 month ago by