4-bit Open on Hugging Face
Parameters
103B
Weights (est.)
≈ 57.8 GB
Mac memory (est.)
96 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/Solar-Open-100B-4bit --prompt "Hello"
Details
- Base model
- upstage/Solar-Open-100B (quantized)
- Vendor
- upstage
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- solar-apache-2.0
- Downloads
- 71 in the last 30 days · 876 all time · 0 likes
- Published
- 2026-01-03 · updated 2026-01-06 (10mo ago)
- Languages
- en, ko
- Tags
- solar_open, upstage, solar, 100b, custom_code
Other MLX builds of upstage/Solar-Open-100B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Solar-Open-100B-4bit (this one) | 4-bit | ≈ 57.8 GB | 96 GB+ | 71 |
| Solar-Open-100B-6bit | 6-bit | ≈ 83.4 GB | 96 GB+ | 52 |
| Solar-Open-100B-8bit | 8-bit | ≈ 109 GB | 128 GB+ | 120 |