4-bit Open on Hugging Face
Parameters
71B
Weights (est.)
≈ 39.7 GB
Mac memory (est.)
48 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/Hermes-4-70B-4bit --prompt "Hello"
Details
- Base model
- NousResearch/Hermes-4-70B (quantized)
- Vendor
- NousResearch
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama3
- Downloads
- 131 in the last 30 days · 1.2K all time · 0 likes
- Published
- 2025-08-26 · updated 2025-08-26 (1y ago)
- Languages
- en
- Tags
- llama, Llama-3.1, instruct, finetune, reasoning, hybrid-mode, chatml, function calling, tool use, json mode, structured outputs, atropos
Other MLX builds of NousResearch/Hermes-4-70B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Hermes-4-70B-4bit (this one) | 4-bit | ≈ 39.7 GB | 48 GB+ | 131 |
| Hermes-4-70B-5bit | 5-bit | ≈ 48.5 GB | 64 GB+ | 82 |
| Hermes-4-70B-6bit | 6-bit | ≈ 57.3 GB | 96 GB+ | 41 |
| Hermes-4-70B-8bit | 8-bit | ≈ 75.0 GB | 96 GB+ | 113 |