Vision GGUF models

17604 GGUF models: models that read images through an mmproj file. Sizes run from 1M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
llava llama 3 8b v1 1
Llama · xtuner
Params8B
Context8K
Smallest4.9 GB
Vision
MI
Ministral 3 3B Instruct 2512
Mistral · ggml-org
Params3.43B
Context256K
Smallest3.7 GB
Vision
MI
Mistralai Shieldstral 1.0 3B
Mistral · Abiray
Params3.43B
Context256K
Q4_K_M2.1 GB
Vision
QW
Qwen3.5 27B Writer V2 Uncensored Heretic
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen3.5 9B Kimi K3 Distilled
Qwen · somenetworktrouble
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
QW
Qwen3.5 4b Agentic Coder v4
Qwen · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
CodingVision
GU
GUI Owl 1.5 8B Think
Gui · mradermacher
Params8.19B
Context32K
Q4_K_M5.0 GB
ReasoningTool useVision
QW
Qwen3.5 9B Star Trek TNG DS9 Heretic Uncensored Thinking MAX NEOCODE
Qwen · DavidAU
Params8.95B
Context256K
Q4_K_M6.8 GB
ReasoningRoleplayVision
QW
Qwen3-Vl-4B-Thinking-1M
Qwen · unsloth
Params4B
Context977K
Q4_K_M2.5 GB
ReasoningVision
QW
Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP
Qwen · luoyumo
Params8.95B
Context256K
Q4_K_M6.8 GB
CodingReasoningRoleplay
SI
Signal 3.8 27B Terse Coder
Signal · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningVision
QW
Qwen3 VL 8B Instruct
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
SK
Skywork Skywork R1V3 38B
Skywork · bartowski
Params32.8B
Context32K
Q4_K_M19.8 GB
Vision
LI
LightOnOCR 3 4B
Lightonocr · richardyoung
Params4.2B
Context256K
Q4_K_M2.7 GB
Vision
QW
Qwopus3.6 27B v2
Qwopus · Jackrong
Params27B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
SA
Salience 1.5 Flash
Salience · bartowski
Params30.5B
Context256K
Q4_K_M18.7 GB
CodingReasoningTool use
QW
Qwen3 VL 30B A3B Thinking
Qwen · bartowski
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningVision
GE
Gemma-4-26B-A4B-It
Gemma · TaterTotterson
Params25.2B
Context256K
Q4_K_M16.9 GB
Vision
LL
Mini Lama 8B Base
Llama · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
Vision
QW
Huihui Qwen3.8 27B Abliterated NVFP4
Qwen · renketong
Params27.3B
Context256K
Smallest19.7 GB
Vision
NE
Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell
Nemotron · Cudecnik
Params124B
Context1024K
Smallest71.6 GB
ReasoningTool useVision
QW
Qwen3.6-35B-A3B
Qwen · AtomicChat
Params447M
Context256K
Smallest17.7 GB
Vision
GR
GRM 3.2 Cliff
Grm · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
Vision
HA
Harmonic Hermes 9B
Harmonic · DJLougen
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
GE
Gemma4 31b Opus Reasoning v5
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningVision
QW
Qwen35B Agent R2 Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
RO
RolmOCR
Rolmocr · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Tool useVision
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · zugquants
Params26.9B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
NE
Nemotron 3.5 Bolt 74B A9B 24GB Metal
Nemotron · UraionLabs
Params74B
Context256K
Smallest24.2 GB
ReasoningTool useVision
QW
MiMo V2.6 Distill Qwen 9B
Qwen · webmp3
Params8.95B
Context256K
Smallest4.1 GB
Vision

Other uses

Keep browsing