LL

codellama_codellama-34b-instruct-hf

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

codellama_codellama-34b-instruct-hf 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).

CodeLlama 34B Instruct in GGUF format for local code generation

CodeLlama 34B Instruct is a 34‑billion‑parameter model focused on coding tasks. It is available in GGUF format, enabling efficient inference with llama.cpp and compatible libraries. The model supports a 16,384‑token context window and is licensed under llama2.

Good at

  • Code generation
  • Debugging assistance
  • API documentation

Limits

  • Large VRAM requirement for full precision
  • No vision or multimodal support
  • License restricts commercial redistribution

Best for

  • Developers needing local code completion
  • Educational coding tools
  • Automated code review scripts

Who it’s for. Engineers and researchers who require a powerful, locally hosted code generation model. The model is ideal for environments where internet access is limited or privacy is critical.

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_S (21.3 GB memory at 8 k context). With 12 GB VRAM, Q4_K_M (22.3 GB) is suitable. For 16 GB VRAM, Q5_K_M (25.9 GB) provides a good balance between quality and memory usage. Estimates are approximate.

What GPU do you need for codellama_codellama-34b-instruct-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: 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 codellama_codellama-34b-instruct-hf quant should you choose?

Q4_K_M is the usual starting point for codellama_codellama-34b-instruct-hf: 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
Licensellama2
Downloads (HF)11,785
Last updated2023-09-27

Frequently asked questions about codellama_codellama-34b-instruct-hf

How much VRAM does codellama_codellama-34b-instruct-hf 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 codellama_codellama-34b-instruct-hf 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 codellama_codellama-34b-instruct-hf 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 codellama_codellama-34b-instruct-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 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download codellama_codellama-34b-instruct-hf GGUF?

The files are on Hugging Face in the TheBloke/CodeLlama-34B-Instruct-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_codellama-34b-instruct-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 34B Instruct on 8 GB VRAM?

The smallest quant that fits is Q4_K_S, which requires about 21.3 GB of VRAM at 8 k context. 8 GB VRAM is insufficient for any quant of this model.

Does this model support image inputs?

No, CodeLlama 34B Instruct is a text‑only model with no vision capabilities.

Is the model licensed for commercial use?

The model is licensed under llama2, which allows commercial use but requires compliance with the license terms.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other medium models

All medium models →