LL

CodeLlama-7B-KStack-clean

LlamaGGUF by bartowskiUpdated 2024-05-25
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

CodeLlama-7B-KStack-clean 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 23 quants, from 1.5 GB (IQ1_S) to 27.0 GB (F32).

CodeLlama-7B-KStack-clean, a 6.74B coding model in GGUF format

CodeLlama-7B-KStack-clean is a 6.74B parameter Llama family model focused on coding tasks. It supports a 16384 token context window and is released under the apache-2.0 license. The model is available in multiple quantizations for different memory budgets.

Good at

  • Coding assistance
  • Code generation
  • Debugging suggestions

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No chat template specified

Best for

  • Developers needing lightweight code models
  • Embedded coding assistants
  • Local code completion

Who it’s for. This model is suitable for developers and researchers who need a dedicated coding model that can run locally. It is ideal for environments with limited GPU memory and for those who prefer open‑source licensing.

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 →
IQ4_NL3.8 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 →
Q8_07.2 GB 12.0 GB
Too big Get file →
F3227.0 GB 31.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M. For 12 GB VRAM, Q4_K_M or Q5_K_S are suitable. For 16 GB VRAM, Q5_K_M or Q6_K provide higher quality while staying within memory limits. Estimates are approximate.

What GPU do you need for CodeLlama-7B-KStack-clean?

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 Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 32 GB VRAM: the best quant that fits is F32 (27.0 GB file, about 31.7 GB in use).

Which CodeLlama-7B-KStack-clean quant should you choose?

Q4_K_M is the usual starting point for CodeLlama-7B-KStack-clean: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 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 bybartowski
FamilyLlama
Licenseapache-2.0
Downloads (HF)969
Last updated2024-05-25

Frequently asked questions about CodeLlama-7B-KStack-clean

How much VRAM does CodeLlama-7B-KStack-clean 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-KStack-clean 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-KStack-clean 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 17 more.

What context length does CodeLlama-7B-KStack-clean 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-KStack-clean GGUF?

The files are on Hugging Face in the bartowski/CodeLlama-7B-KStack-clean-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-KStack-clean use?

Hugging Face lists the license as apache-2.0. 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 IQ1_S on 8 GB VRAM?

Yes, IQ1_S has an estimated memory usage of 6.3 GB at 8k context, fitting comfortably on 8 GB VRAM.

Is there a quant that fits 12 GB VRAM?

Q4_K_M uses about 8.9 GB at 8k context, which fits within 12 GB VRAM.

Does this model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of CodeLlama-7b-hf

Similar models

Browse all →

More from bartowski

All by bartowski →

More Llama models

All Llama →

Other small models

All small models →