Vicuna GGUF models

158 GGUF models in the Vicuna family, quantized by 70 uploaders. Sizes run from 68M to 32.5B parameters. The longest trained context is 32K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
VI
vicuna 13B v1.5
Vicuna · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
VI
vicuna 7B v1.5
Vicuna · TheBloke
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 7b v1.3
Vicuna · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 7b v1.3
Vicuna · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
VI
lmsys_vicuna-13b-v1.5-16k
Vicuna · TheBloke
Params13B
Context16K
Q4_K_M7.9 GB
GGUF
VI
Vicuna 7b v1.3
Vicuna · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
VI
vicuna-7b-v1.5-safeunlearning
Vicuna · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 7b v1.3
Vicuna · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 7b v1.3
Vicuna · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 7b v1.3
Vicuna · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 13b v1.5
Vicuna · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
VI
felixchao_vicuna-33b-coder
Vicuna · TheBloke
Params32.5B
Context2K
Q4_K_M19.6 GB
Coding
VI
lmsys_vicuna-33b-v1.3
Vicuna · TheBloke
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
VI
lmsys_vicuna-7b-v1.5-16k
Vicuna · TheBloke
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF
VI
vicuna 33b v1.3
Vicuna · shaowenchen
Params32.5B
Context2K
Smallest13.5 GB
GGUF
VI
kevinpro_vicuna-7b-cot
Vicuna · TheBloke
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 13b v1.5
Vicuna · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
VI
kevinpro_vicuna-13b-cot
Vicuna · TheBloke
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
VI
Vicuna 13b Free
Vicuna · mradermacher
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
VI
vicuna 7b v1.5 imatrix
Vicuna · duyntnet
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
VI
vicuna-160m
Vicuna · RichardErkhov
Params162M
Context2K
Q4_K_M0.1 GB
GGUF
VI
vicuna 13b v1.5 16k
Vicuna · shaowenchen
Params13B
Context16K
Smallest5.4 GB
GGUF
VI
vicuna-7b-v1.5-uncensored
Vicuna · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
VI
vicuna-68m
Vicuna · RichardErkhov
Params68M
Context2K
Q4_K_M0.0 GB
GGUF
VI
vicuna 13b v1.5 16k imatrix
Vicuna · duyntnet
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
VI
Vicuna 7b v1.5 16k
Vicuna · duyntnet
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 7b v1.1
Vicuna · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 13b Cocktail
Vicuna · mradermacher
Params13B
Context2K
Q4_K_M7.9 GB
Roleplay
VI
Vicuna 7b v1.5
Vicuna · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
VI
Vicuna 7b v1.5
Vicuna · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF

About the Vicuna GGUF models

Vicuna is represented on ggufmodels.com by 158 GGUF models, quantized by 70 uploaders on Hugging Face. The most downloaded are vicuna 13B v1.5, vicuna 7B v1.5 and Vicuna 7b v1.3. Parameter counts run from 68M to 32.5B, and the longest trained context window is 32K tokens.

A Q4_K_M file of a Vicuna model is between 0.0 to 19.6 GB, which is the quant most people start with. Most files come from mradermacher (29), tensorblock (16) and RichardErkhov (12). The quants you will meet most often are Q2_K (85), Q4_K_M (79), Q8_0 (69) and Q3_K_M (68), where the number is how many models offer that quant.

Frequently asked questions

Which Vicuna GGUF should I download?

The most downloaded Vicuna GGUF here is vicuna 13B v1.5. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Vicuna model need?

Q4_K_M files of Vicuna models on this site range from 0.0 to 19.6 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Vicuna GGUF files come from?

The most common quantizers here are mradermacher, tensorblock and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing