LL

llava v1.6 vicuna 7b

LLaVAGGUF by cjpaisUpdated 2024-03-07
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

llava v1.6 vicuna 7b 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 7 quants, from 2.8 GB (Q3_K_XS) to 7.2 GB (Q8_0).

LLaVA 1.6 Vicuna 7B – multimodal LLM with vision support

LLaVA 1.6 Vicuna 7B is a 6.74 billion‑parameter model that combines a Vicuna base with vision capabilities. It was trained on 558K image‑text pairs and 158K instruction‑follow data. The model is available in multiple GGUF quantizations.

Good at

  • Vision‑enabled chat
  • Multimodal instruction following
  • Research prototyping

Limits

  • No vision support in some quant files
  • Requires 8 k context for estimates
  • License is Apache‑2.0

Best for

  • Image captioning
  • Visual question answering
  • Multimodal research

Who it’s for. Researchers and hobbyists working on computer vision and NLP who need a lightweight, open‑source multimodal model. The model is suitable for academic projects and experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_XS2.8 GB 5.4 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_XS (2.77 GB file, 7.6 GB memory at 8k context). If 12 GB VRAM is available, Q8_0 (7.16 GB file, 12 GB memory) offers full precision. Lower‑bit quants like Q3_K_M or Q4_K_M provide a balance between size and performance.

What GPU do you need for llava v1.6 vicuna 7b?

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 Q3_K_XS (2.8 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which llava v1.6 vicuna 7b quant should you choose?

Q4_K_M is the usual starting point for llava v1.6 vicuna 7b: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 Q3_K_XS at 2.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bycjpais
FamilyLLaVA
Licenseapache-2.0
Downloads (HF)863
Last updated2024-03-07

Frequently asked questions about llava v1.6 vicuna 7b

How much VRAM does llava v1.6 vicuna 7b 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 llava v1.6 vicuna 7b on an 8 GB GPU?

Yes, with Q3_K_XS: the 2.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llava v1.6 vicuna 7b GGUF?

It depends on the quant: Q3_K_XS is 2.8 GB, Q3_K_M is 3.3 GB, Q4_K_M is 4.1 GB, Q5_K_S is 4.7 GB, Q5_K_M is 4.8 GB, Q6_K is 5.5 GB and 1 more.

What context length does llava v1.6 vicuna 7b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download llava v1.6 vicuna 7b GGUF?

The files are on Hugging Face in the cjpais/llava-v1.6-vicuna-7b-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 llava v1.6 vicuna 7b use?

Hugging Face lists the license as apache-2.0. 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 LLaVA 1.6 Vicuna 7B on 8 GB VRAM?

Yes, the Q3_K_XS quantization requires about 7.6 GB of VRAM at 8k context, fitting within an 8 GB budget.

Does this model support vision tasks?

Yes, the model includes vision capabilities and is trained on image‑text pairs.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from cjpais

All by cjpais →

More LLaVA models

All LLaVA →

Other small models

All small models →