codellama CodeLlama 34b hf needs about 22.3 GB of memory at Q4_K_M (a 20.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 12.5 GB (Q2_K) to 27.7 GB (Q6_K).
codellama CodeLlama 34b hf is a 33.7B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 16K tokens. The repository has 21 quant files, from 12.5 GB (Q2_K) to 27.7 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.5 GB | 14.6 GB | Too big | Get file → | |
| IQ3_XS | 13.9 GB | 16.0 GB | Too big | Get file → | |
| Q3_K_S | 14.6 GB | 16.7 GB | Too big | Get file → | |
| IQ3_S | 14.7 GB | 16.8 GB | Too big | Get file → | |
| IQ3_M | 15.2 GB | 17.3 GB | Too big | Get file → | |
| Q3_K | 16.3 GB | 18.4 GB | Too big | Get file → | |
| Q3_K_M | 16.3 GB | 18.4 GB | Too big | Get file → | |
| Q3_K_L | 17.8 GB | 19.9 GB | Too big | Get file → | |
| IQ4_XS | 18.2 GB | 20.3 GB | Too big | Get file → | |
| Q4_0 | 19.1 GB | 21.2 GB | Too big | Get file → | |
| Q4_K_S | 19.2 GB | 21.3 GB | Too big | Get file → | |
| IQ4_NL | 19.2 GB | 21.3 GB | Too big | Get file → | |
| Q4_K | 20.2 GB | 22.3 GB | Too big | Get file → | |
| Q4_K_M | 20.2 GB | 22.3 GB | Too big | Get file → | |
| Q4_1 | 21.1 GB | 23.3 GB | Too big | Get file → | |
| Q5_0 | 23.2 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_S | 23.2 GB | 25.3 GB | Too big | Get file → | |
| Q5_K | 23.8 GB | 25.9 GB | Too big | Get file → | |
| Q5_K_M | 23.8 GB | 25.9 GB | Too big | Get file → | |
| Q5_1 | 25.3 GB | 27.4 GB | Too big | Get file → | |
| Q6_K | 27.7 GB | 29.8 GB | Too big | Get file → |
What GPU do you need for codellama CodeLlama 34b hf?
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 IQ3_XS (13.9 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (21.1 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (27.7 GB file, about 29.8 GB in use).
Which codellama CodeLlama 34b hf quant should you choose?
Q4_K_M is the usual starting point for codellama CodeLlama 34b hf: it balances file size and quality well. Here it is a 20.2 GB file.
If memory is tight, the smallest file is Q2_K at 12.5 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
Frequently asked questions about codellama CodeLlama 34b hf
How much VRAM does codellama CodeLlama 34b hf need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 20.2 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 CodeLlama 34b hf 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 CodeLlama 34b hf GGUF?
It depends on the quant: Q2_K is 12.5 GB, IQ3_XS is 13.9 GB, Q3_K_S is 14.6 GB, IQ3_S is 14.7 GB, IQ3_M is 15.2 GB, Q3_K is 16.3 GB and 15 more.
What context length does codellama CodeLlama 34b hf support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.
Where can I download codellama CodeLlama 34b hf GGUF?
The files are on Hugging Face in the RichardErkhov/codellama_-_CodeLlama-34b-hf-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.