LL

CodeLlama 70B Python

LlamaGGUF by TheBlokeUpdated 2024-01-31
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant25.5 GB
Quick answer

CodeLlama 70B Python needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

CodeLlama 70B Python – a large language model specialized for Python code generation

CodeLlama 70B Python is a 70‑billion‑parameter Llama‑based model fine‑tuned for Python code synthesis. It supports up to 4096 context tokens and is available in multiple GGUF quantizations. The model is licensed under the llama2 license and is intended for commercial and research use.

Good at

  • Python code completion
  • Python code understanding
  • Large‑scale code generation

Limits

  • No vision support
  • Maximum context 4096 tokens
  • Requires GPU for efficient inference

Best for

  • Developers needing large‑scale Python code synthesis
  • Research on code generation models
  • Integrating code generation into local applications

Who it’s for. This model is suitable for developers, researchers, and enterprises that require a powerful Python‑focused code generation tool. It can be run locally with llama.cpp or compatible GUIs, provided sufficient GPU memory is available.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 27.3 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_M33.3 GB 35.1 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
Q4_038.9 GB 40.7 GB
Too big Get file →
Q4_K_S39.2 GB 41.1 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_047.5 GB 49.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K or Q4_K_S (≈42 GB memory at 8k context). For 16 GB VRAM, Q5_K_M or Q5_0 (≈52 GB memory). For 32 GB VRAM, Q3_K_M or Q3_K_L (≈36–39 GB memory). Estimates are approximate.

What GPU do you need for CodeLlama 70B Python?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q2_K (25.5 GB file, about 28.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which CodeLlama 70B Python quant should you choose?

Q4_K_M is the usual starting point for CodeLlama 70B Python: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 25.5 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

Architecturellama
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licensellama2
Downloads (HF)4,766
Last updated2024-01-31

Frequently asked questions about CodeLlama 70B Python

How much VRAM does CodeLlama 70B Python need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 70B Python on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CodeLlama 70B Python GGUF?

It depends on the quant: Q2_K is 25.5 GB, Q3_K_S is 29.9 GB, Q3_K_M is 33.3 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB, Q4_K_S is 39.2 GB and 4 more.

What context length does CodeLlama 70B Python support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download CodeLlama 70B Python GGUF?

The files are on Hugging Face in the TheBloke/CodeLlama-70B-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 70B Python 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 70B Python on 8 GB VRAM?

Only with the lowest quantizations such as Q4_K or Q4_K_S, which require around 42 GB of VRAM at 8k context. 8 GB VRAM is insufficient for any quantization of this model.

Does this model support long‑context beyond 4096 tokens?

No, the model is trained with a maximum context of 4096 tokens and does not support longer contexts.

What license applies to this model?

The model is released under the llama2 license, which allows commercial and research use.

Other GGUFs of CodeLlama-70b-Python-hf

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other large models

All large models →