LL

codellama_codellama-34b-python-hf

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant14.2 GB
Quick answer

codellama_codellama-34b-python-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 12 quants, from 14.2 GB (Q2_K) to 35.9 GB (Q8_0).

CodeLlama 34B Python in GGUF format for local inference

CodeLlama 34B Python is a 34‑billion‑parameter model focused on coding tasks. It is available in GGUF format with multiple quantisations, enabling deployment on a range of hardware. The model supports a 16,384‑token context window and is released under the llama2 license.

Good at

  • Python code generation
  • Debugging assistance
  • API implementation

Limits

  • Large VRAM requirement for full precision
  • No vision capabilities
  • Requires GPU for efficient inference

Best for

  • Developers writing Python scripts
  • Automating code reviews
  • Generating API stubs

Who it’s for. This model is intended for developers and researchers who need a high‑capacity code generation model that can run locally. It is suitable for users with access to GPUs that can accommodate the memory demands of the chosen quantisation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K14.2 GB 16.3 GB
Too big Get file →
Q3_K_S14.6 GB 16.7 GB
Too big Get file →
Q3_K_M16.3 GB 18.4 GB
Too big Get file →
Q3_K_L17.8 GB 19.9 GB
Too big Get file →
Q4_019.1 GB 21.2 GB
Too big Get file →
Q4_K_S19.1 GB 21.3 GB
Too big Get file →
Q4_K_M20.2 GB 22.3 GB
Too big Get file →
Q5_023.2 GB 25.3 GB
Too big Get file →
Q5_K_S23.2 GB 25.3 GB
Too big Get file →
Q5_K_M23.8 GB 25.9 GB
Too big Get file →
Q6_K27.7 GB 29.8 GB
Too big Get file →
Q8_035.9 GB 38.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (≈21.3 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (≈22.3 GB) or Q5_K_S (≈25.3 GB) are suitable. Higher‑bit quantisations such as Q6_K or Q8_0 require 30 GB+ VRAM and are recommended only for high‑end GPUs.

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 (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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.7 GB file, about 29.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.9 GB file, about 38.0 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 20.2 GB file.

The Q8_0 file is 35.9 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 14.2 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

Architecturellama
Parameters33.7B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licensellama2
Downloads (HF)6,259
Last updated2023-09-27

Frequently asked questions about codellama_codellama-34b-python-hf

How much VRAM does codellama_codellama-34b-python-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-python-hf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.3 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: Q2_K is 14.2 GB, Q3_K_S is 14.6 GB, Q3_K_M is 16.3 GB, Q3_K_L is 17.8 GB, Q4_0 is 19.1 GB, Q4_K_S is 19.1 GB and 6 more.

What context length does codellama_codellama-34b-python-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-python-hf GGUF?

The files are on Hugging Face in the TheBloke/CodeLlama-34B-Python-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_codellama-34b-python-hf 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 34B Python on 8 GB VRAM?

Only with a low‑bit quantisation such as Q4_K_S, which still requires about 21 GB of VRAM at 8k context. 8 GB VRAM is insufficient for any supported quantisation.

Does this model support image input?

No, CodeLlama 34B Python is a text‑only model and does not process visual data.

What license applies to this model?

The model is released under the llama2 license, which allows commercial use with attribution.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other medium models

All medium models →