Meta
CodeLlama 13B Instruct (13B parameters) requires approximately 21.9 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 26 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run CodeLlama 13B Instruct on your machine.
Run
lms load CodeLlama-13b-Instruct-hf && lms server startQuick specs
About this model
Related models
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | — |
Q3_K_S | 3 | 6.4 GB | Low | — |
NVFP4 | 4 | 7.3 GB | Medium | — |
Q4_K_M | 4 | 7.9 GB | Medium | — |
Q5_K_M | 5 | 9.4 GB | High | — |
Q6_K | 6 | 10.7 GB | High | — |
Q8_0 | 8 | 13.9 GB | Very High | — |
F16 | 16 | 26.7 GB | Maximum | — |
Quality benchmarks
Coding
Source: official · 2023-08-24
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
CodeLlama 13B Instruct (13B parameters) requires approximately 21.9 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Mac mini M4 64GB can run CodeLlama 13B Instruct with a compatibility score of 73/100. It provides 64 GB of memory and achieves approximately 9.6 tokens per second.
The recommended quantization for CodeLlama 13B Instruct is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for CodeLlama 13B Instruct: RTX 5090 32GB (score: 82/100), RTX PRO 4500 Blackwell 32GB (score: 82/100), AMD Instinct MI100 32GB (score: 82/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, CodeLlama 13B Instruct is well-suited for coding. It was designed with these use cases in mind.
See also
