LL

CodeLlama 70b Python Hf

LlamaGGUF by mradermacherUpdated 2024-09-10
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant25.5 GB
Quick answer

CodeLlama 70b Python Hf 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 12 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

CodeLlama 70B Python – 70 billion‑parameter code model

CodeLlama 70B Python is a 70 billion‑parameter Llama‑based model fine‑tuned for Python code generation. It supports up to 4096‑token context and is available in multiple GGUF quantizations. The model is designed for code synthesis and understanding.

Good at

  • Python code completion
  • Code generation
  • Code understanding

Limits

  • No vision support
  • No instruction or chat mode
  • Requires large VRAM for full precision

Best for

  • Automated code generation
  • Python debugging assistance
  • Code documentation generation

Who it’s for. Developers and researchers needing a large‑scale Python code model. The model is suitable for commercial and research use under Meta’s license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 27.3 GB
Too big Get file →
IQ3_XS28.3 GB 30.2 GB
Too big Get file →
IQ3_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
IQ3_M30.9 GB 32.8 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 →
IQ4_XS37.2 GB 39.0 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_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 Q2_K (25.46 GB file, ~28.6 GB memory). For 12 GB VRAM, Q3_K_S (29.92 GB file, ~33.1 GB memory). For 16 GB VRAM, Q4_K_M (41.42 GB file, ~44.6 GB memory). Estimates are approximate.

What GPU do you need for CodeLlama 70b 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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ3_XS (28.3 GB file, about 31.5 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 Hf quant should you choose?

Q4_K_M is the usual starting point for CodeLlama 70b Python Hf: 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 bymradermacher
FamilyLlama
Downloads (HF)1,586
Last updated2024-09-10

Frequently asked questions about CodeLlama 70b Python Hf

How much VRAM does CodeLlama 70b Python Hf 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 Hf 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 Hf GGUF?

It depends on the quant: Q2_K is 25.5 GB, IQ3_XS is 28.3 GB, IQ3_S is 29.9 GB, Q3_K_S is 29.9 GB, IQ3_M is 30.9 GB, Q3_K_M is 33.3 GB and 6 more.

What context length does CodeLlama 70b Python Hf 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 Hf GGUF?

The files are on Hugging Face in the mradermacher/CodeLlama-70b-Python-hf-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run CodeLlama 70B Python on 8 GB VRAM?

Use the Q2_K quantization; it requires about 28.6 GB of VRAM at 8k context, so 8 GB is insufficient.

Does this model support long context beyond 4096 tokens?

No, the model is trained with a maximum context of 4096 tokens.

Is there a license for commercial use?

The model is governed by Meta’s license; a custom commercial license is available at Meta’s website.

Other GGUFs of CodeLlama-70b-Python-hf

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →