Parameters
8.0B
Weights (est.)
≈ 16.1 GB
Mac memory (est.)
24 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-3-Llama-3.1-8B-MLX --prompt "Hello"
Details
- Base model
- NousResearch/Hermes-3-Llama-3.1-8B (finetune)
- Vendor
- NousResearch
- Task
- Text generation
- Quantisation
- Not stated
- Licence
- llama3
- Downloads
- 142 in the last 30 days · 1.2K all time · 1 likes
- Published
- 2025-04-29 · updated 2025-04-29 (1y ago)
- Languages
- en
- Tags
- llama, Llama-3, instruct, finetune, chatml, gpt4, synthetic data, distillation, function calling, json mode, axolotl, roleplaying
Other MLX builds of NousResearch/Hermes-3-Llama-3.1-8B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Hermes-3-Llama-3.1-8B-3bit | 3-bit | ≈ 3.5 GB | 8 GB+ | 71 |
| Hermes-3-Llama-3.1-8B-MLX (this one) | — | ≈ 16.1 GB | 24 GB+ | 142 |