v2.2 · 2026-06-12

VISION / MULTIMODAL MODEL — RUNTIME REQUIREMENTS

·CLIP vision encoder with LLaVA multimodal projector; GGUF deployments may require a matching mmproj/projector file or a runtime that bundles it.

·Local vision inference may require a separate projector/mmproj file depending on runtime.

·RAM and VRAM estimates are derived from GGUF/Ollama package size plus conservative overhead; KV cache, image resolution, batch size, GPU offload and runtime support can materially change memory needs.

LLaVA 1.6 Vicuna 7B

llava-1-6-vicuna-7b

VISION-LANGUAGE

LLaVA 1.6 Vicuna 7B is a 7B vision language model profile for local AI planning. This page records provider, license, context, quantization, hardware-fit estimates, setup hints, source links, and caveats so readers do not choose a model by name alone.

PROVIDER

LLaVA / liuhaotian

FAMILY

LLaVA-NeXT / LLaVA 1.6

MODEL TYPE

vision-language

PARAMETERS

MODALITIES

text, image

ARCHITECTURE

LLaVA multimodal adapter over Vicuna 7B v1.5 / Llama architecture, with a CLIP vision encoder and multimodal projector.

CONTEXT WINDOW

4,096 tokens

TRAINING TOKENS

—

RELEASE DATE

2024-01-30

LICENSE & LINKS

Llama 2 Community Licenselicense text

MODEL CARD

huggingface.co/liuhaotian/llava-v1.6-vicuna-7b

HUGGING FACE

liuhaotian/llava-v1.6-vicuna-7b

GGUF REPOSITORIES

cjpais/llava-v1.6-vicuna-7b-gguf community conversion

Community GGUF conversion with Q4_K_M, Q5_K_M and Q8_0 file listings; not an official LLaVA GGUF repository.

SETUP HINTS

OLLAMA

Run `ollama run llava:7b-v1.6-vicuna-q4_K_M`; Ollama bundles the vision path for its LLaVA package.

LM STUDIO

Use a LLaVA-capable GGUF workflow and ensure that the matching multimodal projector is selected if the UI asks for one.

LLAMA.CPP

Use a current llama.cpp LLaVA/multimodal binary and pass the matching `--mmproj` projector file when using raw GGUF files.

QUANTIZATION FILE SIZES (GGUF)

Q4_K_M

4.08 GB

Q5_K_M

4.78 GB

Q8_0

7.16 GB

Quantization note: Q4_K_M for broad local image-chat use; Q5_K_M when memory allows.

RAM / VRAM ESTIMATES

MIN RAM

8 GB

COMFORTABLE RAM

16 GB

MIN VRAM

6 GB

COMFORTABLE VRAM

8 GB

These are conservative local-inference estimates, not official hardware requirements.

HARDWARE FIT

CPU only (no GPU)

limited

8 GB RAM

limited

16 GB RAM

yes

32 GB RAM

yes

8 GB VRAM

yes

12 GB VRAM

yes

24 GB VRAM

yes

Apple Silicon (unified memory)

yes

Hardware fit values are conservative local-inference estimates based on GGUF size plus runtime and KV-cache overhead. Actual requirements depend on context length, quantization, runtime, GPU offload, and other running apps.

BEST FOR

·Local image captioning and visual question-answering demos

·Small multimodal chat workflows

·Research or hobbyist use on commodity hardware

·Testing LLaVA-compatible local runtimes

AVOID IF

·You need production-grade OCR or document intelligence

·You need a current commercial-friendly permissive license stack

·You need structured tool calling

·You need long-context text-only chat

CAVEATS

·Community GGUF conversion is not an official LLaVA artifact.