4-bit Open on Hugging Face
Parameters
9.0B
Weights (est.)
≈ 5.0 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Tmax-9B-MLX-4bit --prompt "Hello"
Details
- Base model
- allenai/tmax-9b (quantized)
- Vendor
- Ai2 · OLMo
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 50 in the last 30 days · 397 all time · 1 likes
- Published
- 2026-06-24 · updated 2026-06-25 (4mo ago)
- Tags
- qwen3_5
Other MLX builds of allenai/tmax-9b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Tmax-9B-MLX-4bit (this one) | 4-bit | ≈ 5.0 GB | 8 GB+ | 50 |
| Tmax-9B-MLX-6bit | 6-bit | ≈ 7.3 GB | 16 GB+ | 27 |
| Tmax-9B-MLX-8bit | 8-bit | ≈ 9.5 GB | 16 GB+ | 51 |
| Tmax-9B-MLX-bf16 | bf16 | ≈ 17.9 GB | 24 GB+ | 29 |