LL

Llama 3 13B

LlamaGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters13.3B
Context8K
Layers56
Architecturellama
Smallest quant5.1 GB
Quick answer

Llama 3 13B needs about 10.4 GB of memory at Q4_K_M (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 5.1 GB (Q2_K) to 14.1 GB (Q8_0).

Llama 3 13B – 13.3B parameter Llama model in GGUF format

Llama 3 13B is a 13.3B parameter Llama architecture model. It supports a 8192 token context window. The model is available in multiple quantizations from Q2_K to Q8_0.

Good at

  • Large context handling
  • Versatile language tasks
  • Low‑memory quant options

Limits

  • No vision support
  • License type is other
  • No mixture of experts

Best for

  • Chat applications
  • Text generation
  • Fine‑tuning on small datasets

Who it’s for. Developers and researchers needing a mid‑size Llama model with flexible quantization. Suitable for local deployment on GPUs with moderate VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.1 GB 7.5 GB
Tight Get file →
IQ3_XS5.7 GB 8.0 GB
Too big Get file →
Q3_K_S5.9 GB 8.3 GB
Too big Get file →
IQ3_S5.9 GB 8.3 GB
Too big Get file →
IQ3_M6.1 GB 8.5 GB
Too big Get file →
Q3_K_M6.5 GB 8.9 GB
Too big Get file →
Q3_K_L7.1 GB 9.4 GB
Too big Get file →
IQ4_XS7.3 GB 9.7 GB
Too big Get file →
Q4_K_S7.7 GB 10.0 GB
Too big Get file →
Q4_K_M8.1 GB 10.4 GB
Too big Get file →
Q5_K_S9.2 GB 11.6 GB
Too big Get file →
Q5_K_M9.4 GB 11.8 GB
Too big Get file →
Q6_K10.9 GB 13.3 GB
Too big Get file →
Q8_014.1 GB 16.5 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (est. 10.4 GB) or Q3_K_M (est. 8.9 GB). For 12 GB VRAM use Q5_K_M (est. 11.8 GB). For 16 GB VRAM use Q6_K (est. 13.3 GB).

What GPU do you need for Llama 3 13B?

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 IQ3_XS (5.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.4 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.9 GB file, about 13.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.1 GB file, about 16.5 GB in use).

Which Llama 3 13B quant should you choose?

Q4_K_M is the usual starting point for Llama 3 13B: it balances file size and quality well. Here it is a 8.1 GB file.

The Q8_0 file is 14.1 GB, about 1.7 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 5.1 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
Parameters13.3B
Layers56
Trained context8,192 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licenseother
Downloads (HF)567
Last updated2024-05-06

Frequently asked questions about Llama 3 13B

How much VRAM does Llama 3 13B need?

About 10.4 GB at Q4_K_M with an 8K context window. That is the 8.1 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 3 13B on an 8 GB GPU?

Yes, with IQ3_XS: the 5.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3 13B GGUF?

It depends on the quant: Q2_K is 5.1 GB, IQ3_XS is 5.7 GB, Q3_K_S is 5.9 GB, IQ3_S is 5.9 GB, IQ3_M is 6.1 GB, Q3_K_M is 6.5 GB and 8 more.

What context length does Llama 3 13B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.9 GB at 8K and 1.9 GB at 8K.

Where can I download Llama 3 13B GGUF?

The files are on Hugging Face in the mradermacher/Llama-3-13B-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 3 13B use?

Hugging Face lists the license as other. 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 this model on 8 GB VRAM?

Use Q4_K_M or Q3_K_M quantizations; they require about 10.4 GB or 8.9 GB of VRAM at 8k context.

What is the smallest quant available?

Q2_K is the smallest at 5.11 GB file size, estimating 7.5 GB VRAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →