LL

Llama 2 Coder 7B

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

Llama 2 Coder 7B needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.8 GB (Q2_K) to 7.2 GB (Q8_0).

Llama 2 Coder 7B – a 7B parameter code‑focused model in GGUF format

Llama 2 Coder 7B is a 7‑billion‑parameter model fine‑tuned on CodeAlpaca 20k with QLoRA. It is available in multiple GGUF quantisations and supports up to 4096 context tokens. The model is released under the Apache‑2.0 license.

Good at

  • Coding tasks and instruction following
  • Fast inference with low‑bit quantisations
  • LLM inference on local hardware

Limits

  • No vision or multimodal support
  • Requires 8‑k context for full memory estimates
  • License is Apache‑2.0, not commercial by default

Best for

  • Local code generation
  • Debugging assistance
  • Learning programming concepts

Who it’s for. Developers and hobbyists who need a lightweight code model for local inference. The model runs well on GPUs with 8 GB VRAM or more, depending on quantisation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 5.5 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q5_04.7 GB 7.3 GB
Tight Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (≈8.9 GB RAM) or Q5_K_S (≈9.4 GB RAM). For 12 GB VRAM, Q5_K_M or Q6_K are suitable. Higher‑bit quants like Q8_0 need 12 GB VRAM and more memory. File sizes range from 2.83 GB (Q2_K) to 7.16 GB (Q8_0).

What GPU do you need for Llama 2 Coder 7B?

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: the best quant that fits is Q3_K_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which Llama 2 Coder 7B quant should you choose?

Q4_K_M is the usual starting point for Llama 2 Coder 7B: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.8 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
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licenseapache-2.0
Downloads (HF)3,913
Last updated2023-09-27

Frequently asked questions about Llama 2 Coder 7B

How much VRAM does Llama 2 Coder 7B need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Llama 2 Coder 7B on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 2 Coder 7B GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, Q4_0 is 3.8 GB, Q4_K_S is 3.9 GB and 6 more.

What context length does Llama 2 Coder 7B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Llama 2 Coder 7B GGUF?

The files are on Hugging Face in the TheBloke/Llama-2-Coder-7B-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 Llama 2 Coder 7B use?

Hugging Face lists the license as apache-2.0. 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 Llama 2 Coder 7B on 8 GB VRAM?

Yes, with a Q4_K_M or Q5_K_S quantisation the model uses about 8.9–9.4 GB RAM, fitting within 8 GB VRAM with some headroom.

Does this model support image input?

No, Llama 2 Coder 7B is a text‑only model and has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other small models

All small models →