VI

lmsys_vicuna-13b-v1.5-16k

VicunaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters13B
Context16K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

lmsys_vicuna-13b-v1.5-16k 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 with 16K context, GGUF format

Vicuna 13B v1.5 16K is a chat assistant fine‑tuned from Llama 2. It supports up to 16,384 tokens per context and is released under the Llama 2 Community License. The model is available in multiple GGUF quantisations for efficient local inference.

Good at

  • Chat‑style conversations
  • Instruction following
  • Long‑context handling

Limits

  • No vision support
  • Requires GPU for best performance
  • License limits commercial use

Best for

  • Research on LLM chatbots
  • Hobbyist experimentation
  • Educational demos

Who it’s for. Researchers and hobbyists working in natural language processing, machine learning, and artificial intelligence. The model is suited for those who need a large‑context chat assistant for experimentation and study.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 12.6 GB
Too big Get file →
Q3_K_S5.7 GB 12.9 GB
Too big Get file →
Q3_K_M6.3 GB 13.5 GB
Too big Get file →
Q3_K_L6.9 GB 14.1 GB
Too big Get file →
Q4_07.4 GB 14.6 GB
Too big Get file →
Q4_K_S7.4 GB 14.6 GB
Too big Get file →
Q4_K_M7.9 GB 15.1 GB
Too big Get file →
Q5_09.0 GB 16.2 GB
Too big Get file →
Q5_K_S9.0 GB 16.2 GB
Too big Get file →
Q5_K_M9.2 GB 16.4 GB
Too big Get file →
Q6_K10.7 GB 17.9 GB
Too big Get file →
Q8_013.8 GB 21.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (7.87 GB file, ~15.1 GB RAM). For 12 GB VRAM, Q5_K_M (9.23 GB file, ~16.4 GB RAM) is suitable. For 16 GB VRAM, Q6_K (10.68 GB file, ~17.9 GB RAM) provides higher quality. Estimates are approximate.

What GPU do you need for lmsys_vicuna-13b-v1.5-16k?

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 lmsys_vicuna-13b-v1.5-16k quant should you choose?

Q4_K_M is the usual starting point for lmsys_vicuna-13b-v1.5-16k: 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 context16,384 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyVicuna
Licensellama2
Downloads (HF)2,081
Last updated2023-09-27

Frequently asked questions about lmsys_vicuna-13b-v1.5-16k

How much VRAM does lmsys_vicuna-13b-v1.5-16k 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 lmsys_vicuna-13b-v1.5-16k 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 lmsys_vicuna-13b-v1.5-16k 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 lmsys_vicuna-13b-v1.5-16k support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 6.7 GB at 8K and 13.4 GB at 16K.

Where can I download lmsys_vicuna-13b-v1.5-16k GGUF?

The files are on Hugging Face in the TheBloke/vicuna-13B-v1.5-16K-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 lmsys_vicuna-13b-v1.5-16k 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?

Yes, with Q4_K_M quantisation the model file is 7.87 GB and requires about 15.1 GB of RAM at 8 k context.

Does this model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

It is released under the Llama 2 Community License Agreement.

Other GGUFs of vicuna-13b-v1.5-16k

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Vicuna models

All Vicuna →

Other medium models

All medium models →