Downloads · 30 days
46
10% of all-time downloads
Qwen3.5-0.8B-Base-Quant
thwrhrt/Qwen3.5-0.8B-Base-Quant
Qwen3.5-0.8B-Base-Quant is a text generation model from thwrhrt. Use it when you need the model to write or continue text.
All-time downloads
450
Public
Repo size
2 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf2 GB · 100%
At a glance
- Task
- Text Generation
- Access
- Public
- Created
- Mar 24, 2026
- Updated
- Mar 25, 2026
- SHA
- bfcea9e8
Try a prompt
Model card
From the Hugging Face model README
Qwen3.5-0.8B GGUF Quantizations
Converted from: Qwen/Qwen3.5-0.8B-Base
Quantizations
- Q2_K → smallest, fastest
- Q3_K_M → balanced
- Q4_K_M → recommended
- Q5_K_M → highest quality
Recommended: Q4_K_M (best balance of speed and quality)
Q2_K → ~200MB
Q4_K_M → ~500MB
Q5_K_M → ~650MB
Tested on
- LM Studio ✔
- llama.cpp ✔
Notes
- Converted using llama.cpp
- No LoRA / base model only
license: apache 2.0
- Task
- Text Generation
- Created
- Mar 24, 2026
- Updated
- Mar 25, 2026