4-bit Open on Hugging Face
Parameters
36B
Weights (est.)
≈ 20.3 GB
Mac memory (est.)
32 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/Seed-OSS-36B-Instruct-4bit --prompt "Hello"
Details
- Base model
- ByteDance-Seed/Seed-OSS-36B-Instruct (quantized)
- Vendor
- ByteDance-Seed
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 139 in the last 30 days · 2.2K all time · 3 likes
- Published
- 2025-08-21 · updated 2025-08-21 (1y ago)
- Languages
- en, zh
- Tags
- seed_oss, vllm
Other MLX builds of ByteDance-Seed/Seed-OSS-36B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Seed-OSS-36B-Instruct-4bit (this one) | 4-bit | ≈ 20.3 GB | 32 GB+ | 139 |
| Seed-OSS-36B-Instruct-8bit | 8-bit | ≈ 38.4 GB | 48 GB+ | 56 |