Stockmark-2-100B-Instruct-beta-4bit
mlx-community/Stockmark-2-100B-Instruct-beta-4bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
96B
Weights (est.)
≈ 54.0 GB
Mac memory (est.)
64 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/Stockmark-2-100B-Instruct-beta-4bit --prompt "Hello"
Details
- Base model
- stockmark/Stockmark-2-100B-Instruct-beta (quantized)
- Vendor
- stockmark
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 69 in the last 30 days · 890 all time · 2 likes
- Published
- 2025-03-08 · updated 2025-03-08 (1y ago)
- Languages
- ja, en
- Tags
- llama
Other MLX builds of stockmark/Stockmark-2-100B-Instruct-beta
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Stockmark-2-100B-Instruct-beta-4bit (this one) | 4-bit | ≈ 54.0 GB | 64 GB+ | 69 |
| Stockmark-2-100B-Instruct-beta-8bit | 8-bit | ≈ 102 GB | 128 GB+ | 43 |