VI

vicuna 13B v1.5

VicunaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

vicuna 13B v1.5 needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 5.4 GB (Q2_K) to 13.8 GB (Q8_0).

Vicuna 13B v1.5 – a 13‑billion‑parameter chat model in GGUF format

Vicuna 13B v1.5 is a fine‑tuned Llama 2 model with 13 billion parameters. It is available in multiple GGUF quantisations and supports 4096‑token context. The model is licensed under the Llama 2 Community License Agreement.

Good at

  • Chat‑style dialogue
  • Instruction following
  • Research prototyping

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • Large VRAM needed for higher‑bit quantisations

Best for

  • Local chatbot demos
  • Academic research on instruction tuning
  • Fine‑tuning experiments

Who it’s for. Researchers, hobbyists, and developers who need a chat‑capable LLM for local inference. The model is suited for those who can manage the GPU or CPU memory requirements of a 13 billion‑parameter model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 9.3 GB
Too big Get file →
Q3_K_S5.7 GB 9.5 GB
Too big Get file →
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.8 GB
Too big Get file →
Q4_07.4 GB 11.2 GB
Too big Get file →
Q4_K_S7.4 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →
Q5_09.0 GB 12.8 GB
Too big Get file →
Q5_K_S9.0 GB 12.8 GB
Too big Get file →
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →
Q8_013.8 GB 17.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (est. 15.1 GB) or Q5_0 (16.2 GB). For 12 GB VRAM, Q4_0 (14.6 GB) or Q5_K_S (16.2 GB) are suitable. Higher‑bit quantisations such as Q6_K or Q8_0 exceed typical consumer GPU limits.

What GPU do you need for vicuna 13B v1.5?

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 Q4_K_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which vicuna 13B v1.5 quant should you choose?

Q4_K_M is the usual starting point for vicuna 13B v1.5: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 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 5.4 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
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyVicuna
Licensellama2
Downloads (HF)3,038
Last updated2023-09-27

Frequently asked questions about vicuna 13B v1.5

How much VRAM does vicuna 13B v1.5 need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 vicuna 13B v1.5 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of vicuna 13B v1.5 GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.4 GB and 6 more.

What context length does vicuna 13B v1.5 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download vicuna 13B v1.5 GGUF?

The files are on Hugging Face in the TheBloke/vicuna-13B-v1.5-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 vicuna 13B v1.5 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 Vicuna 13B v1.5 on 8 GB VRAM?

With Q4_K_M or Q5_0 quantisations the estimated VRAM usage is around 15–16 GB, which exceeds 8 GB. Lower‑bit options are not available for this model.

Does Vicuna 13B v1.5 support vision tasks?

No. The model is a text‑only LLM and does not include vision capabilities.

Other GGUFs of vicuna-13b-v1.5

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Vicuna models

All Vicuna →

Other medium models

All medium models →