LL

CodeLlama 7b Hf

LlamaGGUF by mradermacherUpdated 2024-09-11
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

CodeLlama 7b Hf needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 1.5 GB (IQ1_S) to 5.5 GB (Q6_K).

CodeLlama 7b Hf – a 6.74B parameter code generation model

CodeLlama 7b Hf is a 6.74B parameter Llama‑based model fine‑tuned for code synthesis and understanding. It supports only text input and output and is licensed under the llama2 license. The model was trained on a dataset from January 2023 to July 2023.

Good at

  • Code completion
  • Code infilling
  • General code synthesis

Limits

  • No vision support
  • No instruction or chat mode
  • Requires 8‑k context for full performance

Best for

  • Writing code snippets
  • Debugging assistance
  • Generating documentation comments

Who it’s for. Developers and researchers needing a lightweight code generation model. The model is suitable for integration into IDEs or code review tools where only text generation is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 6.3 GB
Fits Get file →
IQ1_M1.7 GB 6.4 GB
Fits Get file →
IQ2_XXS1.9 GB 6.6 GB
Fits Get file →
IQ2_XS2.0 GB 6.8 GB
Fits Get file →
IQ2_S2.2 GB 7.0 GB
Fits Get file →
IQ2_M2.4 GB 7.2 GB
Fits Get file →
Q2_K2.5 GB 7.3 GB
Tight Get file →
IQ3_XXS2.6 GB 7.4 GB
Tight Get file →
IQ3_XS2.8 GB 7.6 GB
Tight Get file →
IQ3_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
IQ3_M3.1 GB 7.9 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
IQ4_XS3.6 GB 8.4 GB
Too big Get file →
Q4_03.8 GB 8.6 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (1.53 GB file, 6.3 GB memory) or IQ1_M (1.65 GB file, 6.4 GB memory). If 12‑GB VRAM is available, IQ2_S (2.2 GB file, 7 GB memory) or Q2_K (2.53 GB file, 7.3 GB memory) provide better quality. Larger quants such as Q5_K_M (4.78 GB file, 9.6 GB memory) require 16‑GB VRAM or more.

What GPU do you need for CodeLlama 7b 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: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).

Which CodeLlama 7b Hf quant should you choose?

Q4_K_M is the usual starting point for CodeLlama 7b Hf: it balances file size and quality well. Here it is a 4.1 GB file.

If memory is tight, the smallest file is IQ1_S at 1.5 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
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama2
Downloads (HF)3,126
Last updated2024-09-11

Frequently asked questions about CodeLlama 7b Hf

How much VRAM does CodeLlama 7b Hf need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 7b Hf on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of CodeLlama 7b Hf GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB, IQ2_M is 2.4 GB and 15 more.

What context length does CodeLlama 7b 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 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download CodeLlama 7b Hf GGUF?

The files are on Hugging Face in the mradermacher/CodeLlama-7b-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 7b 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 7b Hf on 8 GB VRAM?

Yes, the IQ1_S quant uses 6.3 GB memory at 8‑k context, fitting within 8 GB VRAM.

Does this model support chat or instruction following?

No, the base model only supports code completion and infilling, not chat or instruction modes.

What license applies to this model?

The model is released under the llama2 license, as specified in the parent model card.

Other GGUFs of CodeLlama-7b-hf

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →