Configuration Parsing Warning:Config file config.json cannot be fetched (too big)
Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)
Qwen3.5-0.8B-Instruct-NF4
NF4 4-bit quantized version of Qwen/Qwen3.5-0.8B, optimized for low VRAM environments.
Quantization Details
- Method: bitsandbytes NF4 (4-bit NormalFloat)
- Compute dtype: float16
- Double quantization: enabled
- Coverage: includes vision encoder (unlike AWQ)
- Model size: ~823 MB (original ~1.6 GB)
License
Apache 2.0 — based on Qwen/Qwen3.5-0.8B by Alibaba Cloud.
- Downloads last month
- 25