VI

Vicuna 7b v1.3

VicunaGGUF by mradermacherUpdated 2024-09-08
Download on Hugging Face
Parameters6.74B
Context2K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

Vicuna 7b v1.3 needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.5 GB (IQ1_S) to 5.5 GB (Q6_K).

Vicuna 7b v1.3 – a 6.74B parameter chat model in GGUF format

Vicuna 7b v1.3 is a 6.74B parameter language model fine‑tuned from LLaMA on ShareGPT conversations. It is available in multiple GGUF quantizations and is suitable for research and hobbyist use. The model is released under a non‑commercial license.

Good at

  • Chat‑style dialogue
  • Instruction following
  • Text generation

Limits

  • No vision support
  • Context limited to 2048 tokens
  • Non‑commercial license

Best for

  • Research prototypes
  • Chatbot demos
  • Text completion tasks

Who it’s for. Researchers and hobbyists working on natural language processing, machine learning, and artificial intelligence. The model is ideal for experimentation and educational projects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 3.1 GB
Fits Get file →
IQ1_M1.7 GB 3.2 GB
Fits Get file →
IQ2_XXS1.9 GB 3.4 GB
Fits Get file →
IQ2_XS2.0 GB 3.6 GB
Fits Get file →
IQ2_S2.2 GB 3.8 GB
Fits Get file →
IQ2_M2.4 GB 3.9 GB
Fits Get file →
Q2_K2.5 GB 4.1 GB
Fits Get file →
IQ3_XXS2.6 GB 4.2 GB
Fits Get file →
IQ3_XS2.8 GB 4.4 GB
Fits Get file →
IQ3_S2.9 GB 4.5 GB
Fits Get file →
Q3_K_S2.9 GB 4.5 GB
Fits Get file →
IQ3_M3.1 GB 4.7 GB
Fits Get file →
Q3_K_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_L3.6 GB 5.2 GB
Fits Get file →
IQ4_XS3.6 GB 5.2 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_K_S3.9 GB 5.4 GB
Fits Get file →
Q4_K_M4.1 GB 5.7 GB
Fits Get file →
Q5_K_S4.7 GB 6.2 GB
Fits Get file →
Q5_K_M4.8 GB 6.4 GB
Fits Get file →
Q6_K5.5 GB 7.1 GB
Fits Get file →

For 8 GB VRAM, use IQ2_XS (2.03 GB) or Q4_0 (3.83 GB) as they fit comfortably. If 12 GB VRAM is available, IQ3_S (2.95 GB) or Q4_K_M (4.08 GB) provide higher quality. Larger models like Q6_K (5.53 GB) require 10.3 GB memory at 8k context and are best on high‑end GPUs.

What GPU do you need for Vicuna 7b 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: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).

Which Vicuna 7b v1.3 quant should you choose?

Q4_K_M is the usual starting point for Vicuna 7b v1.3: it balances file size and quality well. Here it is a 4.1 GB file.

If memory is tight, the smallest file is IQ1_S at 1.5 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
Parameters6.74B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyVicuna
Downloads (HF)1,704
Last updated2024-09-08

Frequently asked questions about Vicuna 7b v1.3

How much VRAM does Vicuna 7b v1.3 need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Vicuna 7b v1.3 on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Vicuna 7b v1.3 GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB, IQ2_M is 2.4 GB and 18 more.

What context length does Vicuna 7b 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 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download Vicuna 7b v1.3 GGUF?

The files are on Hugging Face in the mradermacher/vicuna-7b-v1.3-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Vicuna 7b v1.3 on 8 GB VRAM?

Yes, use a quant such as IQ2_XS (2.03 GB) or Q4_0 (3.83 GB).

Does Vicuna 7b v1.3 support image input?

No, the model has no vision capabilities.

What license applies to Vicuna 7b v1.3?

The model is released under a non‑commercial license.

Other GGUFs of vicuna-7b-v1.3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Vicuna models

All Vicuna →

Other small models

All small models →