VI

vicuna 33b v1.3

VicunaGGUF by shaowenchenUpdated 2023-09-27
Download on Hugging Face
Parameters32.5B
Context2K
Layers60
Architecturellama
Smallest quant13.5 GB
Quick answer

vicuna 33b v1.3 needs about 33.2 GB of memory at Q4_K (a 19.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 14 quants, from 13.5 GB (Q2_K) to 34.6 GB (Q8_0).

Vicuna 33b v1.3 – 32.5B parameter LLaMA model

Vicuna 33b v1.3 is a 32.5B parameter LLaMA‑based model. It supports a 2048 token context window and is available in multiple GGUF quantizations. The model is released under an other license.

Good at

  • Large language generation
  • High‑capacity reasoning
  • Long‑form content creation

Limits

  • No vision support
  • Context limited to 2048 tokens
  • License not specified for commercial use

Best for

  • Research prototyping
  • Academic experimentation
  • Custom fine‑tuning

Who it’s for. Researchers and developers who need a large LLaMA model for text‑only tasks and can manage the memory requirements. The model is suitable for environments that support GGUF and llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.5 GB 17.3 GB
Too big Get file →
Q3_K_S14.1 GB 17.8 GB
Too big Get file →
Q3_K15.8 GB 19.5 GB
Too big Get file →
Q3_K_L17.3 GB 21.1 GB
Too big Get file →
Q4_018.4 GB 22.1 GB
Too big Get file →
Q4_K_S18.4 GB 22.2 GB
Too big Get file →
Q4_K19.6 GB 23.4 GB
Too big Get file →
Q4_120.4 GB 24.1 GB
Too big Get file →
Q5_022.4 GB 26.2 GB
Too big Get file →
Q5_K_S22.4 GB 26.2 GB
Too big Get file →
Q5_K23.0 GB 26.8 GB
Too big Get file →
Q5_124.4 GB 28.2 GB
Too big Get file →
Q6_K26.7 GB 30.5 GB
Too big Get file →
Q8_034.6 GB 38.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 13.5 GB, estimated 27.1 GB memory at 8k context). For 12 GB VRAM, Q3_K_S (14.06 GB, 27.7 GB memory) is a good balance. For 16 GB VRAM, Q4_0 (18.36 GB, 31.9 GB memory) offers higher quality.

What GPU do you need for vicuna 33b v1.3?

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 Q4_K_S (18.4 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 40.3 GB in use).

Which vicuna 33b v1.3 quant should you choose?

Q4_K (19.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 13.5 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
Parameters32.5B
Layers60
Trained context2,048 tokens
KV cache (fp16)1560 KB per token

Source

Quantized byshaowenchen
FamilyVicuna
Licenseother
Downloads (HF)627
Last updated2023-09-27

Frequently asked questions about vicuna 33b v1.3

How much VRAM does vicuna 33b v1.3 need?

About 33.2 GB at Q4_K with an 8K context window. That is the 19.6 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 33b v1.3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of vicuna 33b v1.3 GGUF?

It depends on the quant: Q2_K is 13.5 GB, Q3_K_S is 14.1 GB, Q3_K is 15.8 GB, Q3_K_L is 17.3 GB, Q4_0 is 18.4 GB, Q4_K_S is 18.4 GB and 8 more.

What context length does vicuna 33b v1.3 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 13.1 GB at 8K and 3.3 GB at 2K.

Where can I download vicuna 33b v1.3 GGUF?

The files are on Hugging Face in the shaowenchen/vicuna-33b-v1.3-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 33b v1.3 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 Q2_K on 8 GB VRAM?

Q2_K requires about 27.1 GB memory at 8k context, so 8 GB VRAM is insufficient.

Which quantization is best for 12 GB VRAM?

Q3_K_S uses 27.7 GB memory at 8k context, which is close to 12 GB VRAM but still exceeds it; consider lower context or larger VRAM.

Does this model support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from shaowenchen

All by shaowenchen →

More Vicuna models

All Vicuna →

Other medium models

All medium models →