IQ3_XXS GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 28129 models have a IQ3_XXS file. Sizes run from 2M to 2450B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2.5 VL 32B Instruct Abliterated
Qwen · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
Vision
NA
VisionPsy Nano 460M Flash GGUFs
Nanovlm · qvac
Params409M
Context8K
Q4_K_M0.3 GB
Vision
QW
JetBrains Qwen3.8 3.6 27B Blend
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
Vision
DE
Deepseek-V3.2
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M405.4 GB
GGUF
SA
Sabi Noema
Sabi · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Tool use
ER
Ernie-4.5-21B-A3B-Pt
Ernie · unsloth
Params21.8B
Context128K
Q4_K_M13.3 GB
GGUF
QW
Qwen3.8 Flash Next GSQ RCO abliterated
Qwen · KilltheSniper
Params177B
Context—
Smallest0.9 GB
GGUF
MI
Devstral-2-123B-Instruct-2512
Mistral · unsloth
Params125B
Context256K
Q4_K_M74.9 GB
Coding
HE
HERO 35B A3B
Hero · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
MI
Mistral-Small-3.1-24B-Instruct-2503
Mistral · unsloth
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision
SE
Seed-Oss-36B-Instruct
Seed · unsloth
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
TE
TerminalHorizon 35B A3B
Terminalhorizon · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
FA
Fara1.5 4B
Fara · bartowski
Params4.21B
Context256K
Q4_K_M2.9 GB
Vision
ME
Medgemma-27B-Text-It
Medgemma · unsloth
Params27B
Context128K
Q4_K_M16.5 GB
ReasoningVision
NE
Nemotron Cascade 2 30B A3B
Nemotron · bartowski
Params31.6B
Context1024K
Q4_K_M24.7 GB
Reasoning
TW
Twilight Embrace 31B
Twilight · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
QW
Dongfangshuo Qwen3.8 27B NSFW v4
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Roleplay
MI
Codestral-22B-v0.1
Mistral · bartowski
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
QW
Qwen3.8 27B Abliterated
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
QW
Qwen3.8 14B Instruct Turbo
Qwen · mradermacher
Params14.7B
Context256K
Q4_K_M9.2 GB
ReasoningTool use
DE
DeepSeek-V2-Lite-Chat
DeepSeek · legraphista
Params15.7B
Context160K
Smallest5.0 GB
GGUF
SA
Sage A1.5 Heretic Abliterated Uncensored
Sage · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
CodingReasoningTool use
WI
Wicked Tutu 31B Final
Wicked · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
QW
Qwen3 235B A22B Instruct 2507
Qwen · bartowski
Params235B
Context256K
Q4_K_M142.6 GB
GGUF
QW
Dongfangshuo Qwen3.8 27B NSFW Novel
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Roleplay
CH
chatterbox
Chatterbox · calcuis
Params264M
Context—
Q4_K_M0.3 GB
GGUF
HO
Holo4 35B A3B
Holo · bartowski
Params34.7B
Context256K
Q4_K_M22.3 GB
Vision
RA
Rainbow AI 12B Unified
Rainbow · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
LI
Ling 3.0 tiny
Ling · NANI-Nithin
Params7.89B
Context128K
Q4_K_M4.8 GB
Reasoning
MI
Source Hf Minicpm V 4.7 1b
MiniCPM · ngquocvinh
Params1.01B
Context256K
Q4_K_M0.7 GB
Vision

Other quants

Keep browsing