LL

codefuse-ai_codefuse-codellama-34b

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant14.2 GB
Quick answer

codefuse-ai_codefuse-codellama-34b needs about 22.3 GB of memory at Q4_K_M (a 20.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 14.2 GB (Q2_K) to 35.9 GB (Q8_0).

CodeFuse-CodeLlama-34B: a 34B code‑focused LLM in GGUF format

CodeFuse-CodeLlama-34B is a 34B parameter model fine‑tuned on 600k code instruction/answer pairs. It supports a 16k context length and is available in multiple quantized GGUF variants. The model is designed for code generation tasks.

Good at

  • Code generation
  • Instruction following
  • Large context handling

Limits

  • No vision support
  • Requires GPU for inference
  • License is other

Best for

  • Writing code snippets
  • Debugging assistance
  • Automating code reviews

Who it’s for. Developers and researchers needing a large code‑centric language model. The model is suitable for local deployment via llama.cpp or compatible libraries.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K14.2 GB 16.3 GB
Too big Get file →
Q3_K_S14.6 GB 16.7 GB
Too big Get file →
Q3_K_M16.3 GB 18.4 GB
Too big Get file →
Q3_K_L17.8 GB 19.9 GB
Too big Get file →
Q4_019.1 GB 21.2 GB
Too big Get file →
Q4_K_S19.1 GB 21.3 GB
Too big Get file →
Q4_K_M20.2 GB 22.3 GB
Too big Get file →
Q5_023.2 GB 25.3 GB
Too big Get file →
Q5_K_S23.2 GB 25.3 GB
Too big Get file →
Q5_K_M23.8 GB 25.9 GB
Too big Get file →
Q6_K27.7 GB 29.8 GB
Too big Get file →
Q8_035.9 GB 38.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K or Q4_K_S (file size 19.05 GB, estimated memory 21.2 GB). For 16 GB VRAM, Q5_K_M (23.84 GB, 25.9 GB). For 32 GB VRAM, Q6_K (27.68 GB, 29.8 GB).

What GPU do you need for codefuse-ai_codefuse-codellama-34b?

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 Q4_K_M (20.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.7 GB file, about 29.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.9 GB file, about 38.0 GB in use).

Which codefuse-ai_codefuse-codellama-34b quant should you choose?

Q4_K_M is the usual starting point for codefuse-ai_codefuse-codellama-34b: it balances file size and quality well. Here it is a 20.2 GB file.

The Q8_0 file is 35.9 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 Q2_K at 14.2 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
Parameters33.7B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licenseother
Downloads (HF)1,439
Last updated2023-09-27

Frequently asked questions about codefuse-ai_codefuse-codellama-34b

How much VRAM does codefuse-ai_codefuse-codellama-34b need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 20.2 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 codefuse-ai_codefuse-codellama-34b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of codefuse-ai_codefuse-codellama-34b GGUF?

It depends on the quant: Q2_K is 14.2 GB, Q3_K_S is 14.6 GB, Q3_K_M is 16.3 GB, Q3_K_L is 17.8 GB, Q4_0 is 19.1 GB, Q4_K_S is 19.1 GB and 6 more.

What context length does codefuse-ai_codefuse-codellama-34b support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download codefuse-ai_codefuse-codellama-34b GGUF?

The files are on Hugging Face in the TheBloke/CodeFuse-CodeLlama-34B-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 codefuse-ai_codefuse-codellama-34b use?

Hugging Face lists the license as other. 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 CodeFuse-CodeLlama-34B on 8 GB VRAM?

Use the Q4_K or Q4_K_S quantized GGUF file; it requires about 21.2 GB of VRAM at 8k context.

Does the model support image input?

No, the model has no vision capabilities.

What context length can it handle?

The model was fine‑tuned with a 4k context but can be fine‑tuned to 16k and supports up to 16384 tokens.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other medium models

All medium models →