CodeLlama 13B Instruct needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 13 quants, from 5.4 GB (Q2_K) to 13.8 GB (Q8_0).
13B CodeLlama Instruct – code‑centric instruction following
CodeLlama 13B Instruct is a 13‑billion‑parameter Llama‑based model fine‑tuned for code generation and instruction compliance. It supports code completion, infilling, and chat interactions. The model is released under the llama2 license.
Good at
- Code completion
- Instruction following
- Code infilling
Limits
- No vision support
- Requires 8‑k context for estimates
- License is llama2
Best for
- Writing code snippets
- Debugging assistance
- Generating documentation
Who it’s for. Developers and researchers needing a code‑focused LLM for building code assistants or automating code generation tasks. The model is suitable for commercial and research use in English and programming languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.4 GB | 12.6 GB | Too big | Get file → | |
| Q3_K_S | 5.7 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_M | 6.3 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_L | 6.9 GB | 14.1 GB | Too big | Get file → | |
| Q4_0 | 7.4 GB | 14.6 GB | Too big | Get file → | |
| Q4_0 | 7.4 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_S | 7.4 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_M | 7.9 GB | 15.1 GB | Too big | Get file → | |
| Q5_0 | 9.0 GB | 16.2 GB | Too big | Get file → | |
| Q5_K_S | 9.0 GB | 16.2 GB | Too big | Get file → | |
| Q5_K_M | 9.2 GB | 16.4 GB | Too big | Get file → | |
| Q6_K | 10.7 GB | 17.9 GB | Too big | Get file → | |
| Q8_0 | 13.8 GB | 21.0 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_0 (7.37 GB, ~14.6 GB RAM). For 12‑GB VRAM, Q5_0 (8.97 GB, ~16.2 GB RAM) is a good balance. For 16‑GB VRAM, Q6_K (10.68 GB, ~17.9 GB RAM) offers higher quality.
What GPU do you need for CodeLlama 13B Instruct?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q4_K_M (7.9 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
Which CodeLlama 13B Instruct quant should you choose?
Q4_K_M is the usual starting point for CodeLlama 13B Instruct: it balances file size and quality well. Here it is a 7.9 GB file.
The Q8_0 file is 13.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 5.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about CodeLlama 13B Instruct
How much VRAM does CodeLlama 13B Instruct need?
About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run CodeLlama 13B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of CodeLlama 13B Instruct GGUF?
It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_0 is 7.4 GB and 7 more.
What context length does CodeLlama 13B Instruct support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 6.7 GB at 8K and 13.4 GB at 16K.
Where can I download CodeLlama 13B Instruct GGUF?
The files are on Hugging Face in the second-state/CodeLlama-13B-Instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does CodeLlama 13B Instruct use?
Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run CodeLlama 13B Instruct on 8 GB VRAM?
Yes, using the Q4_0 quantized file (7.37 GB) will fit within 8 GB VRAM, with an estimated 14.6 GB RAM usage.
Does this model support image input?
No, the model only accepts text input and produces text output.
What license applies to this model?
The model is released under the llama2 license, as stated in the parent model card.