DeepHermes-3-Mistral-24B-Preview-4bit
mlx-community/DeepHermes-3-Mistral-24B-Preview-4bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 13.3 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/DeepHermes-3-Mistral-24B-Preview-4bit --prompt "Hello"
Details
- Base model
- NousResearch/DeepHermes-3-Mistral-24B-Preview (quantized)
- Vendor
- NousResearch
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 44 in the last 30 days · 575 all time · 1 likes
- Published
- 2025-03-14 · updated 2025-03-14 (1y ago)
- Languages
- en
- Tags
- mistral, Mistral-Small, instruct, finetune, chatml, gpt4, synthetic data, distillation, function calling, json mode, axolotl, roleplaying
Other MLX builds of NousResearch/DeepHermes-3-Mistral-24B-Preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepHermes-3-Mistral-24B-Preview-4bit (this one) | 4-bit | ≈ 13.3 GB | 24 GB+ | 44 |
| DeepHermes-3-Mistral-24B-Preview-8bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 61 |
| DeepHermes-3-Mistral-24B-Preview-bf16 | bf16 | ≈ 47.1 GB | 64 GB+ | 34 |