Downloads · 30 days
151
31% of all-time downloads
Qwen3.8-32B-Jumbo-4bit
StargazerLabs/Qwen3.8-32B-Jumbo-4bit
Qwen3.8-32B-Jumbo-4bit is a text generation model from StargazerLabs. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
4-bit quantization of Qwen3.8-32B-Jumbo.
All-time downloads
487
Public
Parameters
31.9B
18.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors18.6 GB · 100%
Parameter types
How the weights are stored.
U3231.5B · 99%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-32B-Jumbo (4-bit)
4-bit quantization of Qwen3.8-32B-Jumbo.
A 76-layer, 31.9B-parameter model created by transplanting the three most-drifted organs from Qwen3.6-27B into Qwen3.8-27B. See the bf16 model card for the full organ selection methodology.
Key Stats
- Parameters: ~31.9B
- Layers: 76
- Precision: 4-bit (mlx-lm quantized)
- MTP Compatible: ~89% drafter acceptance, ~2x speculative decoding speedup
Usage (MLX)
# Standard generation
mlx_vlm.generate \
--model StargazerLabs/Qwen3.8-32B-Jumbo-4bit \
--prompt "Your prompt here" --max-tokens 2048
# With MTP speculative decoding
mlx_vlm.generate \
--model StargazerLabs/Qwen3.8-32B-Jumbo-4bit \
--draft-model mlx-community/Qwen3.8-27B-MTP-4bit \
--prompt "Your prompt here" --max-tokens 2048
Related
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026