llmrun

Best local LLMs for vision

Run local LLMs that handle images, screenshots, and docs across your GPU or Mac. We rank them using the llmrun Composite Score and highlight our top choice for every VRAM tier.

Best for vision on

8 GB12 GB16 GB24 GB32 GB48 GB+

Qwen3.8 27B

Alibaba · Q4_K_M · 17.9 GB · up to 64K context · on RTX 4090

37.6 t/s
A
How to run →

All 123 vision models for 24 GB ↓

Also worth a look

Gemma 4 31B IT

Q4_K_M · 21.7 GB · 32.1 t/s · 32K ctx

Best vision model by memory

Highest llmrun Composite Score that fits each size with at least 16K context and 10 t/s, at a Q3 or better quant. Speed is decode tokens per second on that size's reference GPU. The last row has no memory limit: the best model whatever it needs, on the GPU plan shown. Full ranking

Vision models that run on 24 GB123

Ranked by Composite Score, models without one after. Best quant that fits with a 16K context; speed is decode tokens per second on the reference GPU.

123 models · 101 run great · 12 run well

Featured only

Score: llmrun Score, 100 = average model. Fit: how well it runs on this hardware, S best to F won't fit. Ordered by Score, recency and Fit. How ranking works

Showing compatibility for NVIDIA GeForce RTX 4090

LLM models compatible with NVIDIA GeForce RTX 4090 — ranked by Score, recency and Fit
ModelVRAMScoreFit
Gemma 4 26B A4B IT Qat Q4 0 Unquantized
Q4_K_M·171.1 t/s
16.5 GBS98, Runs great
InternVL3 5 GPT OSS 20B A4B Preview HF
Q4_K_M·179.5 t/s
13.6 GBS99, Runs great
ZAYA1 VL 8B
Q4_K_M·345.7 t/s
7.5 GBS100, Runs great
MiniCPM V 4.7 1B
Q4_K_M·511.9 t/s
1.6 GBS100, Runs great
MinerU2.5 Pro 2605 1.2B
< 16K context fits
Q4_K_M·642.4 t/s
1.1 GBS100, Runs great
Diffusiongemma 26B A4B IT
Q4_K_M·170.7 t/s
16.5 GBS98, Runs great
D1 3B
Q4_K_M·284.9 t/s
2.6 GBS100, Runs great
Granite Vision 4.1 4B
Q4_K_M·228.3 t/s
4.0 GBS100, Runs great
MiniCPM V 4.6
Q4_K_M·579.8 t/s
1.5 GBS100, Runs great
North Micro Vision Instruct
BF16·119.1 t/s
7.1 GBS95, Runs great
MiniCPM V 4.6 Thinking
Q4_K_M·579.8 t/s
1.5 GBS100, Runs great
D1 Omni 600M
Q4_K_M·910.0 t/s
1.2 GBS100, Runs great
MinerU2.5 Pro 2604 1.2B
< 16K context fits
Q4_K_M·642.4 t/s
1.1 GBS100, Runs great
LFM2.5 VL 450M
Q4_K_M·1023.8 t/s
0.8 GBS100, Runs great
ZDTaichu5.0 9B
Q4_K_M·101.4 t/s
9.2 GBS92, Runs great

How much memory do you need for a vision model?

On 8 GB the best vision model is Qwen3.5 9B (score 99). At 12 GB it is Gemma 4 26B A4B IT (score 106). From 16 to 32 GB it is Qwen3.8 27B (score 122). With no memory limit, the best is DeepSeek V4.1 Flash 1017 (score 133). Add a bit more breathing room to your setup when using a vision model with an image encoder alongside the language model; each image loads as extra tokens in the context. Allocate slightly more space than you would for a text-only model of equal size.

Frequently Asked Questions

What is the best local LLM for vision?

On 24 GB, Qwen3.8 27B is the top pick with a score of 122, running at about 38 t/s on RTX 4090. It fits up to 64K tokens of context there. On 8 GB, the best fit is Qwen3.5 9B. With no memory limit, the best is DeepSeek V4.1 Flash 1017. Open a model to see which GPUs and Macs run it.

Can I run a vision model on a laptop or an 8 GB GPU?

Yes. On 8 GB the best pick is Qwen3.5 9B (Q4_K_M, 6.6 GB), which runs at about 46 t/s on RTX 5060. Laptops with 8 to 16 GB of memory can run smaller models in the same way.

Can local models read screenshots and documents?

Vision-language models take an image along with your prompt to answer questions, pull out text, or describe charts. Whether support works depends on the runtime; however, you can run them in Ollama or LM Studio.

Do images need extra memory?

The image encoder bumps up the model size. Each picture turns into hundreds of tokens within the context window, swelling the cache. Bigger images demand even more.