4-bit Open on Hugging Face
Parameters
8.2B
Weights (est.)
≈ 4.6 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/SERA-8B-GA-4bit --prompt "Hello"
Details
- Base model
- allenai/SERA-8B-GA (quantized)
- Vendor
- Ai2 · OLMo
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 36 in the last 30 days · 226 all time · 1 likes
- Published
- 2026-01-27 · updated 2026-01-27 (9mo ago)
- Tags
- qwen3
Other MLX builds of allenai/SERA-8B-GA
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| SERA-8B-GA-4bit (this one) | 4-bit | ≈ 4.6 GB | 8 GB+ | 36 |
| SERA-8B-GA-5bit | 5-bit | ≈ 5.6 GB | 16 GB+ | 15 |
| SERA-8B-GA-6bit | 6-bit | ≈ 6.7 GB | 16 GB+ | 19 |
| SERA-8B-GA-8bit | 8-bit | ≈ 8.7 GB | 16 GB+ | 16 |
| SERA-8B-GA-bf16 | bf16 | ≈ 16.4 GB | 24 GB+ | 13 |