codellama · First MLX build 27 Apr 2025
CodeLlama-34b-Instruct-hf
MLX
Text llama2
A 34B parameter text generation model from codellama, with 2 MLX builds, from 4-bit to 6-bit.
- Parameters
- 34B From Hugging Face
- Quantisation
- 6-bit CodeLlama-34b-Instruct-hf-6bit-mlx
- Memory needed
- 33 GB Estimate, unified memory
- Download
- 27.4 GB Weights, estimated
- Downloads
- 48 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 33 GB at 6-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/CodeLlama-34b-Instruct-hf-6bit-mlx --prompt "Hello"MLX builds
2 on mlx-community| CodeLlama-34b-Instruct-hf-4bit-mlx | 4-bit | 19.0 GB | 24 GB | 46 |
|---|---|---|---|---|
| CodeLlama-34b-Instruct-hf-6bit-mlx | 6-bit | 27.4 GB | 33 GB | 48 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.