prithivMLmods/LensVLM-9B-GGUF overview
LensVLM 9B GGUF LensVLM 9B is a 9 billion parameter vision language model from Apple, built on Qwen3.5 9B, introduced in the paper "LensVLM: Selective Context …
Runs locally from ~879.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| LensVLM-9B.BF16.gguf | GGUF | GGUF | 16.69 GB | Download |
| LensVLM-9B.Q3_K_L.gguf | GGUF | GGUF | 4.59 GB | Download |
| LensVLM-9B.Q3_K_M.gguf | GGUF | GGUF | 4.31 GB | Download |
| LensVLM-9B.Q4_K_M.gguf | GGUF | GGUF | 5.24 GB | Download |
| LensVLM-9B.Q4_K_S.gguf | GGUF | GGUF | 4.98 GB | Download |
| LensVLM-9B.Q5_K_M.gguf | GGUF | GGUF | 6.02 GB | Download |
| LensVLM-9B.Q5_K_S.gguf | GGUF | GGUF | 5.87 GB | Download |
| LensVLM-9B.Q6_K.gguf | GGUF | GGUF | 6.85 GB | Download |
| LensVLM-9B.mmproj-bf16.gguf | GGUF | BF16 | 879.0 MB | Download |
Model Details
| Model ID | prithivMLmods/LensVLM-9B-GGUF |
|---|---|
| Author | prithivMLmods |
| Pipeline | image-text-to-text |
| License | apple-amlr |
| Base model | apple/LensVLM-9B |
| Last modified | 2026-09-23T05:44:22.000Z |
Model README
---
license: apple-amlr
license_link: https://huggingface.co/apple/LensVLM-9B/blob/main/LICENSE
library_name: transformers
base_model:
- apple/LensVLM-9B
tags:
- text-generation-inference
- llama-cpp
- vision-language-model
- long-context
- visual-text-compression
language:
- en
pipeline_tag: image-text-to-text
---
LensVLM-9B-GGUF
> LensVLM-9B is a 9-billion-parameter vision-language model from Apple, built on Qwen3.5-9B, introduced in the paper "LensVLM: Selective Context Expansion for Compressed Visual Representation of Text." Its core mechanism scans a compressed image representation of text — at configurable compression ratios of 5x, 10x, or 15x — and then selectively expands only the pages relevant to a given question back to their uncompressed form via learned tools, allowing the model to process very long documents without holding the entire uncompressed text in context. It's run via the accompanying ml-lensvlm codebase with a simple demo script accepting a text file and a question, and is released under the Apple Machine Learning Research Model License (with the accompanying source code separately licensed under the Apple Sample Code License).
Model Files
| File Name | Quant Type | File Size | File Link | Description |
|-----------|------------|-----------|-----------|-------------|
| LensVLM-9B.BF16.gguf | BF16 | 17.9 GB | Link | Full BF16 weights. Highest quality, largest file size. |
| LensVLM-9B.Q3_K_L.gguf | Q3_K_L | 4.93 GB | Link | Lower quality but usable, good for low RAM availability. |
| LensVLM-9B.Q3_K_M.gguf | Q3_K_M | 4.62 GB | Link | Low quality. |
| LensVLM-9B.Q4_K_M.gguf | Q4_K_M | 5.63 GB | Link | Good quality, default size for most use cases, recommended. |
| LensVLM-9B.Q4_K_S.gguf | Q4_K_S | 5.35 GB | Link | Slightly lower quality with more space savings, recommended. |
| LensVLM-9B.Q5_K_M.gguf | Q5_K_M | 6.47 GB | Link | High quality, recommended. |
| LensVLM-9B.Q5_K_S.gguf | Q5_K_S | 6.31 GB | Link | High quality, recommended. |
| LensVLM-9B.Q6_K.gguf | Q6_K | 7.36 GB | Link | Very high quality, near perfect, recommended. |
| LensVLM-9B.mmproj-bf16.gguf | mmproj-bf16 | 922 MB | Link | Multimodal projection file in BF16 format. Used for vision/language models. |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp
Run prithivMLmods/LensVLM-9B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models