codellama CodeLlama 34b Python hf needs about 10.4 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 17 quants, from 8.9 GB (Q4_K_M) to 23.2 GB (Q5_K_S).
codellama CodeLlama 34b Python hf is a 33.7B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 16K tokens. The repository has 17 quant files, from 8.9 GB (Q4_K_M) to 23.2 GB (Q5_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 8.9 GB | 10.4 GB | Too big | Get file → | |
| Q2_K | 12.5 GB | 14.5 GB | Too big | Get file → | |
| IQ3_XS | 13.9 GB | 16.0 GB | Too big | Get file → | |
| Q3_K_S | 14.6 GB | 16.9 GB | Too big | Get file → | |
| IQ3_S | 14.7 GB | 16.9 GB | Too big | Get file → | |
| IQ3_M | 15.2 GB | 17.6 GB | Too big | Get file → | |
| Q3_K | 16.3 GB | 18.8 GB | Too big | Get file → | |
| Q3_K_M | 16.3 GB | 18.8 GB | Too big | Get file → | |
| Q3_K_L | 17.8 GB | 20.4 GB | Too big | Get file → | |
| IQ4_XS | 18.2 GB | 20.9 GB | Too big | Get file → | |
| Q4_0 | 19.1 GB | 21.8 GB | Too big | Get file → | |
| Q4_K_S | 19.2 GB | 22.0 GB | Too big | Get file → | |
| IQ4_NL | 19.2 GB | 22.0 GB | Too big | Get file → | |
| Q4_K | 20.2 GB | 23.1 GB | Too big | Get file → | |
| Q4_1 | 21.1 GB | 24.2 GB | Too big | Get file → | |
| Q5_0 | 23.2 GB | 26.5 GB | Too big | Get file → | |
| Q5_K_S | 23.2 GB | 26.5 GB | Too big | Get file → |
What GPU do you need for codellama CodeLlama 34b Python hf?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_K_M (8.9 GB file, about 10.4 GB in use).
- 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_K (20.2 GB file, about 23.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_0 (23.2 GB file, about 26.5 GB in use).
Which codellama CodeLlama 34b Python hf quant should you choose?
Q4_K_M is the usual starting point for codellama CodeLlama 34b Python hf: it balances file size and quality well. Here it is a 8.9 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about codellama CodeLlama 34b Python hf
How much VRAM does codellama CodeLlama 34b Python hf need?
About 10.4 GB at Q4_K_M with an 8K context window. That is the 8.9 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 CodeLlama 34b Python hf on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of codellama CodeLlama 34b Python hf GGUF?
It depends on the quant: Q4_K_M is 8.9 GB, 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 and 11 more.
What context length does codellama CodeLlama 34b Python hf support?
The GGUF header lists a trained context length of 16,384 tokens (16K).
Where can I download codellama CodeLlama 34b Python hf GGUF?
The files are on Hugging Face in the RichardErkhov/codellama_-_CodeLlama-34b-Python-hf-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.