CodeLlama 13B TestGen Dart v0.2 needs about 16.4 GB of memory at Q5_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 7.4 GB (Q4_0) to 26.0 GB (F16).
CodeLlama 13B TestGen Dart v0.2 is a 13B-parameter Llama model in GGUF format, quantized by jacobhoffmann. Its trained context length is 16K tokens. The repository has 4 quant files, from 7.4 GB (Q4_0) to 26.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 7.4 GB | 14.6 GB | Too big | Get file → | |
| Q5_K_M | 9.2 GB | 16.4 GB | Too big | Get file → | |
| Q8_0 | 13.8 GB | 21.0 GB | Too big | Get file → | |
| F16 | 26.0 GB | 33.2 GB | Too big | Get file → |
What GPU do you need for CodeLlama 13B TestGen Dart v0.2?
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_0 (7.4 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (26.0 GB file, about 33.2 GB in use).
Which CodeLlama 13B TestGen Dart v0.2 quant should you choose?
Q5_K_M (9.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_0 at 7.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about CodeLlama 13B TestGen Dart v0.2
How much VRAM does CodeLlama 13B TestGen Dart v0.2 need?
About 16.4 GB at Q5_K_M with an 8K context window. That is the 9.2 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 TestGen Dart v0.2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of CodeLlama 13B TestGen Dart v0.2 GGUF?
It depends on the quant: Q4_0 is 7.4 GB, Q5_K_M is 9.2 GB, Q8_0 is 13.8 GB, F16 is 26.0 GB.
What context length does CodeLlama 13B TestGen Dart v0.2 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 TestGen Dart v0.2 GGUF?
The files are on Hugging Face in the jacobhoffmann/CodeLlama-13B-TestGen-Dart_v0.2-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 TestGen Dart v0.2 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.