LL

Code-Llama-3-8B

LlamaGGUF by mradermacherUpdated 2024-05-08
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Code-Llama-3-8B needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 2.0 GB (IQ1_S) to 6.6 GB (Q6_K).

Code‑Llama‑3‑8B: 8B‑parameter code generation model

Code‑Llama‑3‑8B is an 8B‑parameter Llama model fine‑tuned on Code‑290k‑ShareGPT, Code‑Feedback, orca‑math‑word‑problems‑200k and CodeFeedback‑Filtered‑Instruction. It excels at generating code in many languages and providing detailed explanations.

Good at

  • Code generation in Python, Java, JavaScript, Go, C++, Rust, Ruby, SQL, MySQL, R, Julia, Haskell
  • Detailed logic explanations for code
  • Math problem solving

Limits

  • No vision support
  • Requires 8K context for full performance
  • License is llama3

Best for

  • Developing code snippets
  • Debugging assistance
  • Learning programming concepts

Who it’s for. Developers, students, and researchers needing a versatile code generation tool. The model is suitable for those who prefer a lightweight, open‑source solution for coding tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.02 GB) or IQ1_M (2.16 GB). For 12 GB VRAM, IQ2_XS (2.61 GB) or IQ2_S (2.76 GB) are good choices. For 16 GB VRAM, consider IQ3_XS (3.52 GB) or Q3_K_S (3.66 GB).

What GPU do you need for Code-Llama-3-8B?

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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

Which Code-Llama-3-8B quant should you choose?

Q4_K_M is the usual starting point for Code-Llama-3-8B: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.0 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
Parameters8B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3
Downloads (HF)1,674
Last updated2024-05-08

Frequently asked questions about Code-Llama-3-8B

How much VRAM does Code-Llama-3-8B need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Code-Llama-3-8B on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Code-Llama-3-8B GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 15 more.

What context length does Code-Llama-3-8B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Code-Llama-3-8B GGUF?

The files are on Hugging Face in the mradermacher/Code-Llama-3-8B-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 Code-Llama-3-8B use?

Hugging Face lists the license as llama3. 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 Code‑Llama‑3‑8B on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations, which use about 3.6–3.7 GB of VRAM at 8K context.

Does this model support vision tasks?

No, the model only handles text and code generation.

What context length does it support?

It supports up to 8192 tokens, the trained context length.

Other GGUFs of Code-Llama-3-8B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →