LL

CodeLlama 70b Hf

LlamaGGUF by mradermacherUpdated 2024-09-18
Download on Hugging Face
Parameters69B
Context16K
Layers80
Architecturellama
Smallest quant14.5 GB
Quick answer

CodeLlama 70b 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 20 quants, from 14.5 GB (IQ1_S) to 48.8 GB (Q5_K_M).

CodeLlama 70B Hf – large‑scale code generation model

CodeLlama 70B Hf is a 69‑billion‑parameter auto‑regressive model fine‑tuned for code synthesis and understanding. It supports up to 16k training context tokens and 100k inference tokens. The model is released under the llama2 license.

Good at

  • Code completion
  • Code understanding
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License restricts commercial use without permission

Best for

  • Generating long code snippets
  • Analyzing complex codebases
  • Automating code review tasks

Who it’s for. Developers and researchers needing high‑fidelity code generation. The model is suitable for building code assistants, refactoring tools, and educational coding platforms.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S14.5 GB 17.7 GB
Too big Get file →
IQ1_M15.9 GB 19.1 GB
Too big Get file →
IQ2_XXS18.3 GB 21.5 GB
Too big Get file →
IQ2_XS20.3 GB 23.5 GB
Too big Get file →
IQ2_S21.4 GB 24.5 GB
Too big Get file →
IQ2_M23.2 GB 26.4 GB
Too big Get file →
Q2_K25.5 GB 28.6 GB
Too big Get file →
IQ3_XXS26.6 GB 29.8 GB
Too big Get file →
IQ3_XS28.3 GB 31.5 GB
Too big Get file →
IQ3_S29.9 GB 33.1 GB
Too big Get file →
Q3_K_S29.9 GB 33.1 GB
Too big Get file →
IQ3_M30.9 GB 34.1 GB
Too big Get file →
Q3_K_M33.3 GB 36.5 GB
Too big Get file →
Q3_K_L36.1 GB 39.3 GB
Too big Get file →
IQ4_XS36.8 GB 40.0 GB
Too big Get file →
Q4_039.0 GB 42.2 GB
Too big Get file →
Q4_K_S39.2 GB 42.4 GB
Too big Get file →
Q4_K_M41.4 GB 44.6 GB
Too big Get file →
Q5_K_S47.5 GB 50.6 GB
Too big Get file →
Q5_K_M48.8 GB 51.9 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (14.54 GB file, 17.7 GB memory). For 16 GB VRAM use IQ2_M (23.23 GB file, 26.4 GB memory). For 24 GB VRAM use Q4_K_M (41.42 GB file, 44.6 GB memory). Estimates are approximate.

What GPU do you need for CodeLlama 70b 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 IQ2_XS (20.3 GB file, about 23.5 GB in use).
  • 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 Hf quant should you choose?

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

If memory is tight, the smallest file is IQ1_S at 14.5 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 context16,384 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama2
Downloads (HF)3,255
Last updated2024-09-18

Frequently asked questions about CodeLlama 70b Hf

How much VRAM does CodeLlama 70b 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 Hf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CodeLlama 70b Hf GGUF?

It depends on the quant: IQ1_S is 14.5 GB, IQ1_M is 15.9 GB, IQ2_XXS is 18.3 GB, IQ2_XS is 20.3 GB, IQ2_S is 21.4 GB, IQ2_M is 23.2 GB and 14 more.

What context length does CodeLlama 70b 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 2.7 GB at 8K and 5.4 GB at 16K.

Where can I download CodeLlama 70b Hf GGUF?

The files are on Hugging Face in the mradermacher/CodeLlama-70b-hf-i1-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 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 70B Hf on 8 GB VRAM?

Use the IQ1_S quant, which requires about 17.7 GB memory at 8k context. 8 GB VRAM is insufficient for full inference.

Does this model support image inputs?

No, it only accepts text inputs and produces text outputs.

What license applies to this model?

The model is released under the llama2 license, which allows research use but requires permission for commercial deployment.

Other GGUFs of CodeLlama-70b-hf

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →