LL

CodeLlama 70B Instruct

LlamaGGUF by TheBlokeUpdated 2024-01-30
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant25.5 GB
Quick answer

CodeLlama 70B Instruct needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

CodeLlama 70B Instruct – large‑scale code generation model

CodeLlama 70B Instruct is a 69‑billion‑parameter Llama‑based model fine‑tuned for code synthesis and instruction following. It supports a 4096‑token context window and is available in multiple GGUF quantisations. The model is licensed under llama2.

Good at

  • Code completion
  • Instruction‑driven chat
  • Code understanding

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is llama2

Best for

  • Developers needing code generation
  • Educational coding assistants
  • Automated code review tools

Who it’s for. Engineers and researchers who need a powerful code‑centric LLM and have access to sufficient GPU memory. The model is suitable for local deployment via llama.cpp or compatible GUIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 27.3 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_M33.3 GB 35.1 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
Q4_038.9 GB 40.7 GB
Too big Get file →
Q4_K_S39.2 GB 41.1 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_047.5 GB 49.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 8 GB VRAM use Q2_K (25.46 GB file, ~28.6 GB memory at 8 k context). For 12 GB VRAM Q3_K_S (29.92 GB file, ~33.1 GB memory). For 24 GB VRAM Q4_K_M (41.42 GB file, ~44.6 GB memory). Estimates are approximate.

What GPU do you need for CodeLlama 70B Instruct?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q2_K (25.5 GB file, about 28.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which CodeLlama 70B Instruct quant should you choose?

Q4_K_M is the usual starting point for CodeLlama 70B Instruct: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 25.5 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licensellama2
Downloads (HF)1,813
Last updated2024-01-30

Frequently asked questions about CodeLlama 70B Instruct

How much VRAM does CodeLlama 70B Instruct need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 70B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CodeLlama 70B Instruct GGUF?

It depends on the quant: Q2_K is 25.5 GB, Q3_K_S is 29.9 GB, Q3_K_M is 33.3 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB, Q4_K_S is 39.2 GB and 4 more.

What context length does CodeLlama 70B Instruct support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download CodeLlama 70B Instruct GGUF?

The files are on Hugging Face in the TheBloke/CodeLlama-70B-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 70B Instruct 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 70B Instruct on 8 GB VRAM?

Use the Q2_K quantisation; it requires about 28.6 GB of VRAM at 8 k context, which exceeds 8 GB, so it is not feasible on 8 GB VRAM.

What is the context length of this model?

The model supports a maximum context length of 4096 tokens.

Is this model suitable for image generation?

No, the model has no vision capabilities and is focused on text and code.

Other GGUFs of CodeLlama-70b-Instruct-hf

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other large models

All large models →