LL

CodeLlama 34b Instruct Hf

LlamaGGUF by mradermacherUpdated 2024-09-09
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant12.5 GB
Quick answer

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 14 quants, from 12.5 GB (Q2_K) to 35.9 GB (Q8_0).

CodeLlama 34B Instruct – large‑scale code generation model

CodeLlama 34B Instruct is a 33.7 billion‑parameter Llama‑based model fine‑tuned for instruction following and code synthesis. It supports up to 16384 context tokens and is licensed under the llama2 license. The model is available in multiple GGUF quantizations.

Good at

  • Code completion
  • Instruction following
  • General code understanding

Limits

  • No vision support
  • Large VRAM requirement for full precision
  • License restricts commercial use without permission

Best for

  • Developers needing code assistants
  • Research on code generation
  • Building custom code‑centric LLMs

Who it’s for. This model is suitable for developers, researchers, and enterprises that require a powerful code generation tool and have the necessary GPU memory. It is ideal for those who can comply with the llama2 license terms.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.5 GB 14.6 GB
Too big Get file →
IQ3_XS13.9 GB 16.0 GB
Too big Get file →
Q3_K_S14.6 GB 16.7 GB
Too big Get file →
IQ3_S14.7 GB 16.8 GB
Too big Get file →
IQ3_M15.2 GB 17.3 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 →
IQ4_XS18.2 GB 20.3 GB
Too big Get file →
Q4_K_S19.2 GB 21.3 GB
Too big Get file →
Q4_K_M20.2 GB 22.3 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 (file size 19.19 GB, estimated 21.3 GB memory). For 12 GB VRAM, Q4_K_M (20.22 GB, 22.3 GB memory). For 16 GB VRAM, Q5_K_S (23.24 GB, 25.3 GB memory). These estimates are approximate.

What GPU do you need for 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: the best quant that fits is IQ3_XS (13.9 GB file, about 16.0 GB in use).
  • 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 34b Instruct Hf quant should you choose?

Q4_K_M is the usual starting point for 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 12.5 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
Parameters33.7B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama2
Downloads (HF)1,573
Last updated2024-09-09

Frequently asked questions about CodeLlama 34b Instruct Hf

How much VRAM does 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 34b Instruct Hf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CodeLlama 34b Instruct Hf GGUF?

It depends on the quant: Q2_K is 12.5 GB, IQ3_XS is 13.9 GB, Q3_K_S is 14.6 GB, IQ3_S is 14.7 GB, IQ3_M is 15.2 GB, Q3_K_M is 16.3 GB and 8 more.

What context length does 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 34b Instruct Hf GGUF?

The files are on Hugging Face in the mradermacher/CodeLlama-34b-Instruct-hf-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 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?

Use the Q4_K_S quantization; it requires about 21.3 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.

Does this model support image input?

No, the model only processes text input.

What license applies to this model?

The model is licensed under the llama2 license, which may restrict commercial use without permission.

Other GGUFs of CodeLlama-34b-Instruct-hf

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →