KVzap-linear-Qwen3-8B
nvidia/KVzap-linear-Qwen3-8B
- kind
- original
- quant
- bf16 (16-bit)
- family
- qwen
- modality
- other
- root model
- nvidia/KVzap-linear-Qwen3-8B
- provider
- nvidia
- license
- apache-2.0
- language
- —
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 92
- likes
- 2
- created
- —
- last modified
- 2026-01-21T10:45:25+00:00 (2026)
- huggingface
- https://huggingface.co/nvidia/KVzap-linear-Qwen3-8B
- tags
- transformerssafetensorskvzapnvidiapytorchotherdataset:nvidia/Nemotron-Pretraining-Dataset-samplearxiv:2506.05345arxiv:2601.07891arxiv:2505.23416license:apache-2.0endpoints_compatibleregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.