LL

Code Llama Bagel 8B

LlamaGGUF by theprintUpdated 2024-09-28
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant3.7 GB
Quick answer

Code Llama Bagel 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 8 quants, from 3.7 GB (Q3_K_S) to 16.1 GB (BF16).

Code Llama Bagel 8B – a fine‑tuned 8B Llama model for code generation

Code Llama Bagel 8B is a 8.03 billion parameter Llama model fine‑tuned on code and math datasets. It supports ChatML prompts and generates code in many languages with detailed explanations.

Good at

  • Code generation in Python, Java, C++
  • Math problem solving
  • Detailed code explanations

Limits

  • No vision support
  • Requires 8 k context for estimates
  • License is llama3

Best for

  • Developers needing code snippets
  • Educators teaching programming
  • Automated code review tools

Who it’s for. This model is ideal for developers, educators, and researchers who need a reliable code generation tool. It is suitable for projects that require detailed code explanations and support for multiple programming languages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 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_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
BF1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (5.2 GB memory) or Q4_K_M (5.6 GB). For 12 GB VRAM, Q5_K_M (7.3 GB) or Q6_K (8.2 GB) are suitable. Higher precision quants like Q8_0 or BF16 need 10–18 GB VRAM.

What GPU do you need for Code Llama Bagel 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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.0 GB file, about 5.6 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 Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 17.6 GB in use).

Which Code Llama Bagel 8B quant should you choose?

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

The Q8_0 file is 8.5 GB, about 1.7 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 Q3_K_S at 3.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bytheprint
FamilyLlama
Licensellama3
Downloads (HF)1,035
Last updated2024-09-28

Frequently asked questions about Code Llama Bagel 8B

How much VRAM does Code Llama Bagel 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 Bagel 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 Bagel 8B GGUF?

It depends on the quant: Q3_K_S is 3.7 GB, Q3_K_M is 4.0 GB, Q4_K_S is 4.7 GB, Q4_K_M is 4.9 GB, Q5_K_M is 5.7 GB, Q6_K is 6.6 GB and 2 more.

What context length does Code Llama Bagel 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 Bagel 8B GGUF?

The files are on Hugging Face in the theprint/Code-Llama-Bagel-8B 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 Bagel 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 Bagel 8B on 8 GB VRAM?

Yes, using Q4_K_S or Q4_K_M quantizations which require about 5–6 GB memory at 8 k context.

Does this model support image inputs?

No, it only supports text input and does not have vision capabilities.

What prompt format does it use?

It uses the ChatML prompt format for all interactions.

Other GGUFs of Code-Llama-3-8B

Similar models

Browse all →

More from theprint

All by theprint →

More Llama models

All Llama →

Other small models

All small models →