CodeLlama-34b-Instruct-hf-4bit-mlx
mlx-community/CodeLlama-34b-Instruct-hf-4bit-mlx
Text generation · mlx
4-bit Open on Hugging Face
Parameters
34B
Weights (est.)
≈ 19.0 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/CodeLlama-34b-Instruct-hf-4bit-mlx --prompt "Hello"
Details
- Base model
- codellama/CodeLlama-34b-Instruct-hf (quantized)
- Vendor
- codellama
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama2
- Downloads
- 46 in the last 30 days · 1.1K all time · 0 likes
- Published
- 2025-04-28 · updated 2025-04-28 (1y ago)
- Languages
- code
- Tags
- llama, llama-2
Other MLX builds of codellama/CodeLlama-34b-Instruct-hf
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| CodeLlama-34b-Instruct-hf-4bit-mlx (this one) | 4-bit | ≈ 19.0 GB | 24 GB+ | 46 |
| CodeLlama-34b-Instruct-hf-6bit-mlx | 6-bit | ≈ 27.4 GB | 48 GB+ | 46 |