Downloads · 30 days
28
17% of all-time downloads
simaai/Qwen3-8B-GPTQ-Safetensors
Qwen3-8B-GPTQ-Safetensors is a text generation model from simaai. Use it when you need the model to write or continue text. The card lists the license as other.
Pre-LLiMa Hugging Face checkpoint for Sima.ai compilation. Source revision was not captured locally; pin an immutable revision before publication.
Downloads · 30 days
28
17% of all-time downloads
All-time downloads
166
Public
Parameters
8.2B
5.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.1 GB · 100%
How the weights are stored.
I327.6B · 92%
From the Hugging Face model README
Pre-LLiMa Hugging Face checkpoint for Sima.ai compilation. Source revision was not captured locally; pin an immutable revision before publication.
Linear layers and lm_head: GPTQ, symmetric INT4, group size 256, static actorder.HuggingFaceH4/ultrachat_200k, 512 samples, 1024 tokens, batch size 1.EleutherAI/wikitext_document_level, wikitext-2-raw-v1, full run (2026-07-16).
| Checkpoint | Word perplexity |
|---|---|
Qwen/Qwen3-8B | 13.486505 |
| This GPTQ checkpoint | 14.358857 |
python quantize.py --model-path /project/mlasw/share/huggingface/models--Qwen--Qwen3-8B --output-dir /path/to/output
Included: quantized safetensors, tokenizer/configuration, quantize.py, recipe.yaml, and versions.txt.
Saved scales were checked for finite values. Transformers load/generation smoke test is pending before release. Quantization quality can vary by language, prompt format, domain, and context length; validate the compiled deployment on target hardware.