LL

CodeLlama 70b Instruct hf

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

CodeLlama 70b Instruct hf 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 6 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

CodeLlama 70b Instruct hf is a 69B-parameter Llama model in GGUF format, quantized by macadeliccc. Its trained context length is 4K tokens. The repository has 6 quant files, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 27.3 GB
Too big Get file →
Q3_K_M33.3 GB 35.1 GB
Too big Get file →
Q4_038.9 GB 40.7 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_M48.8 GB 50.6 GB
Too big Get file →

What GPU do you need for CodeLlama 70b 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: 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 hf quant should you choose?

Q4_K_M is the usual starting point for CodeLlama 70b Instruct hf: 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 bymacadeliccc
FamilyLlama
Downloads (HF)369
Last updated2024-01-30

Frequently asked questions about CodeLlama 70b Instruct hf

How much VRAM does CodeLlama 70b Instruct hf 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 hf 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 hf GGUF?

It depends on the quant: Q2_K is 25.5 GB, Q3_K_M is 33.3 GB, Q4_0 is 38.9 GB, Q4_K_M is 41.4 GB, Q5_0 is 47.5 GB, Q5_K_M is 48.8 GB.

What context length does CodeLlama 70b Instruct hf 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 hf GGUF?

The files are on Hugging Face in the macadeliccc/CodeLlama-70b-Instruct-hf-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from macadeliccc

All by macadeliccc →

More Llama models

All Llama →

Other large models

All large models →