LensVLM 9B needs about 7.4 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 23 quants, from 0.0 GB to 17.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
LensVLM 9B – a vision language model for compressed text documents
LensVLM 9B is a 9‑billion parameter vision language model that scans compressed images of text and expands relevant pages. It uses the Qwen‑3.5 architecture and supports image input via a multimodal projector. The model is available in multiple GGUF quantizations for llama.cpp.
Good at
- Vision‑to‑text on compressed documents
- Selective context expansion
- Multimodal image and text inference
Limits
- No speculative decoding
- Requires mmproj projector for image input
- License: apple‑amlr
Best for
- Document OCR from compressed PDFs
- Image‑based text extraction
- Multimodal chat with image prompts
Who it’s for. Developers building OCR or document‑analysis tools that need to process compressed images. Researchers exploring selective context expansion in vision language models. Users who prefer open‑source quantized models for local inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ2_M | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q2_K | 3.6 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XXS | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_S | 4.3 GB | 5.8 GB | Fits | Get file → | |
| IQ3_XS | 4.3 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_L | 4.7 GB | 6.2 GB | Fits | Get file → | |
| IQ3_M | 4.8 GB | 6.4 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_0 | 5.5 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_S | 5.5 GB | 7.1 GB | Fits | Get file → | |
| IQ4_NL | 5.8 GB | 7.4 GB | Tight | Get file → | |
| Q4_K_M | 5.8 GB | 7.4 GB | Tight | Get file → | |
| Q4_1 | 5.9 GB | 7.5 GB | Tight | Get file → | |
| Q4_K_L | 6.2 GB | 7.8 GB | Tight | Get file → | |
| Q5_K_S | 6.5 GB | 8.1 GB | Too big | Get file → | |
| Q5_K_M | 6.9 GB | 8.4 GB | Too big | Get file → | |
| Q6_K_S | 7.5 GB | 9.1 GB | Too big | Get file → | |
| Q6_K | 7.8 GB | 9.4 GB | Too big | Get file → | |
| Q6_K_L | 8.1 GB | 9.7 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| BF16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (5.84 GB) or Q4_K_S (5.48 GB) are suitable. With 12 GB VRAM, Q5_K_M (6.88 GB) or Q6_K (7.79 GB) provide higher quality. The smallest file, IQ2_M (3.54 GB), fits 4 GB VRAM but offers lower precision.
What GPU do you need for LensVLM 9B?
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: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_XS (4.3 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_L (6.2 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).
Which LensVLM 9B quant should you choose?
Q4_K_M is the usual starting point for LensVLM 9B: it balances file size and quality well. Here it is a 5.8 GB file.
The Q8_0 file is 9.5 GB, about 1.6 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LensVLM 9B
How much VRAM does LensVLM 9B need?
About 7.4 GB at Q4_K_M with an 8K context window. That is the 5.8 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 LensVLM 9B on an 8 GB GPU?
Yes, with Q4_K_L: the 6.2 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LensVLM 9B GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 3.5 GB, Q2_K is 3.6 GB, IQ3_XXS is 4.1 GB, Q3_K_S is 4.3 GB, IQ3_XS is 4.3 GB and 17 more.
What context length does LensVLM 9B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download LensVLM 9B GGUF?
The files are on Hugging Face in the bartowski/LensVLM-9B-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 LensVLM 9B use?
Hugging Face lists the license as apple-amlr. 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 LensVLM 9B on 8 GB VRAM?
Yes, use Q4_K_M or Q4_K_S quantizations, which require about 7–7.5 GB of VRAM at 8k context.
Does LensVLM support text‑only inference?
Yes, the model accepts text input, but its primary design is for vision‑to‑text tasks.
What license applies to LensVLM 9B?
The model is released under the Apple Machine Learning Research Model License (apple‑amlr).