Downloads · 30 days
0
Qwen3.5-122B-A10B
basecompute/Qwen3.5-122B-A10B
Qwen3.5-122B-A10B is a text generation model from basecompute. Use it when you need the model to write or continue text. It is set up for basert. The card lists the license as apache-2.0.
BaseRT .base builds of Qwen/Qwen3.5-122B-A10B for fast local inference on Apple Silicon (Metal) and NVIDIA GB10 (CUDA).
Access
Public
Updated Sep 14, 2026
Repo size
195 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.base195 GB · 100%
At a glance
- Task
- Text Generation
- Library
- basert
- License
- apache-2.0
- Access
- Public
- Created
- Sep 14, 2026
- Updated
- Sep 14, 2026
- SHA
- 2f3834df
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.5-122B-A10B
BaseRT .base builds of Qwen/Qwen3.5-122B-A10B for fast local inference on Apple Silicon (Metal) and NVIDIA GB10 (CUDA).
Files
| File | Precision | Size |
|---|---|---|
Qwen3.5-122B-A10B-Q4.base | Q4 | 69 GB |
Qwen3.5-122B-A10B-Q8.base | Q8 | 126 GB |
Usage
curl -LsSf https://basecompute.co/install.sh | sh
basert pull basecompute/Qwen3.5-122B-A10B
basert chat basecompute/Qwen3.5-122B-A10B
Built and measured at baseRT commit hf.
Released under the apache-2.0 license, inherited from the base model.
- Task
- Text Generation
- Library
- basert
- License
- apache-2.0
- Created
- Sep 14, 2026
- Updated
- Sep 14, 2026