DeepHermes-3-Llama-3-3B-Preview-4bit
mlx-community/DeepHermes-3-Llama-3-3B-Preview-4bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
3.2B
Weights (est.)
≈ 1.8 GB
Mac memory (est.)
8 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/DeepHermes-3-Llama-3-3B-Preview-4bit --prompt "Hello"
Details
- Base model
- NousResearch/DeepHermes-3-Llama-3-3B-Preview (quantized)
- Vendor
- NousResearch
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama3
- Downloads
- 37 in the last 30 days · 520 all time · 0 likes
- Published
- 2025-03-14 · updated 2025-03-14 (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/DeepHermes-3-Llama-3-3B-Preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepHermes-3-Llama-3-3B-Preview-4bit (this one) | 4-bit | ≈ 1.8 GB | 8 GB+ | 37 |
| DeepHermes-3-Llama-3-3B-Preview-8bit | 8-bit | ≈ 3.4 GB | 8 GB+ | 28 |
| DeepHermes-3-Llama-3-3B-Preview-bf16 | bf16 | ≈ 6.4 GB | 16 GB+ | 32 |
| DeepHermes-3-Llama-3-3B-Preview-MLX | — | ≈ 6.4 GB | 16 GB+ | 29 |