tcclaviger
/

Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-512k-ctx-W4A16

Text Generation

mixture-of-experts

code generation

Mixture of Experts

mixture of experts

8 active experts

optional thinking

compressed-tensors

Model card Files Files and versions

Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-512k-ctx-W4A16 / generation_config.json

Rob P Smith

Configure Git LFS for large model files

42ae119 14 days ago

history blame contribute delete

95 Bytes

	{
	"_from_model_config": true,
	"eos_token_id": 151645,
	"transformers_version": "4.57.1"
	}