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
GL
Huihui GLM 4.7 Flash Abliterated
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
GGUF
LA
Laguna-S-2.1
Laguna · unsloth
Params118B
Context256K
Q4_K_M73.1 GB
GGUF
MI
minmax
Minmax · Kutches
Params20.1B
Context—
Q4_K_M11.5 GB
GGUF
QW
Suri Qwen 3.8 27B Companion
Qwen · SpaceTimee
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
QW
Signal 3.8 27B
Qwen · agentionai
Params27.3B
Context—
Q4_K_M17.0 GB
GGUF
SM
Smollm3-3B
SmolLM · unsloth
Params3.08B
Context64K
Q4_K_M1.9 GB
GGUF
NE
Nvidia-Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Nemotron · unsloth
Params31.6B
Context1024K
Q4_K_M23.9 GB
ReasoningVision
AL
Source Hf Aliceai T5 35b A0.6B
Aliceai · ngquocvinh
Params34.6B
Context128K
Q4_K_M21.0 GB
Coding
QW
Qwen3 VL 32B Instruct
Qwen · bartowski
Params32.8B
Context256K
Q4_K_M19.8 GB
Vision
MI
Ministral-3-8B-Reasoning-2512
Mistral · unsloth
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningVision
QW
Qwen3 30B A3B Abliterated Erotic
Qwen · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
GGUF
MI
MiniMax M3.1 Flash
Minimax · unsloth
Params426B
Context1024K
Smallest0.5 GB
GGUF
OC
Occamy 1.0 Abliterated
Occamy · SC117
Params34.7B
Context256K
Q4_K_M16.5 GB
ReasoningVision
QW
Qwen3-4B-Thinking-2507
Qwen · unsloth
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
GO
Goetia 26B A4B v1.7
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
LF
LFM2.5-24B-A2B
Lfm · NANI-Nithin
Params24B
Context128K
Q4_K_M14.5 GB
GGUF
GE
Gemma 4 Orthia 31B
Gemma · mradermacher
Params32.1B
Context256K
Q4_K_M19.5 GB
Roleplay
DE
DeepSeek-V2-Lite
DeepSeek · legraphista
Params15.7B
Context160K
Smallest5.0 GB
GGUF
GL
GLM 4.6V Flash
GLM · bartowski
Params9.4B
Context128K
Q4_K_M6.2 GB
Vision
DE
DeepSeek R1 Distill Llama 70B
DeepSeek · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
Reasoning
GE
Gemma 4 31B It Heretic
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Coding
QW
Qwen2.5 VL 32B Instruct Unredacted MAX
Qwen · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
Vision
QW
Qwen3.8 27B Uncensored Heretic Abliterated
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
LL
Meta llama_Meta Llama 3 70B Instruct
Llama · ThomasBaruzier
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
DE
DeepSeek Coder V2 Lite Instruct Abliterated
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
LY
Lythri 4B A2B
Lythri · mradermacher
Params4.63B
Context128K
Q4_K_M3.4 GB
GGUF
QW
Qwen3.8 27B Uncensored Heretic v3
Qwen · OS-Software
Params27B
Context256K
Q4_K_M16.1 GB
Vision
GP
OpenAI Gpt Oss 20B Claude 4.5 Opus Heretic Uncensored
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
Reasoning
QW
Qwen3.8 Flash Next GSQ RCO abliterated
Qwen · ScottzillaSystems
Params177B
Context—
Smallest0.9 GB
GGUF
AR
Artemis 31B v1.2 Abliterix v2
Artemis · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF

Other quants

Keep browsing