IQ2_XXS GGUF models

Importance-matrix 2-bit quant. Extreme compression with a large quality cost. 26647 models have a IQ2_XXS file. Sizes run from 2M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Phind CodeLlama 34B v2
Llama · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
GL
GLM 4.6
GLM · unsloth
Params357B
Context198K
Q4_K_M215.6 GB
GGUF
MI
Minimax-M2
Minimax · unsloth
Params230B
Context192K
Q4_K_M138.3 GB
GGUF
LA
Laguna XS 2.1
Laguna · bartowski
Params33.4B
Context256K
Q4_K_M20.5 GB
GGUF
QW
Qwen3-Vl-8B-Thinking
Qwen · unsloth
Params8.19B
Context256K
Q4_K_M5.0 GB
ReasoningVision
GE
Gemma 4 E2B It Heretic v1
Gemma · mradermacher
Params4.63B
Context128K
Q4_K_M3.4 GB
Vision
QW
Qwen3.5 397B A17B
Qwen · bartowski
Params403B
Context256K
Q4_K_M248.3 GB
Vision
VE
Veloxy Titan 32B Vision
Veloxy · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
CodingReasoningVision
PA
Pantheon Reasoning 26B A4B 1.1 V2
Pantheon · bartowski
Params26B
Context256K
Q4_K_M18.8 GB
ReasoningRoleplay
OR
Ornith 1.0 35B
Ornith · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Vision
PH
Phi 3 mini 128k instruct GGUF Imatrix smashed
Phi · PrunaAI
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
GE
Gemma 4 Writers 31B
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
DE
DeepSeek V3.1
DeepSeek · bartowski
Params670B
Context160K
Q4_K_M409.2 GB
GGUF
FU
Functiongemma-270M-It
Functiongemma · unsloth
Params268M
Context32K
Q4_K_M0.3 GB
GGUF
GE
TangYuGe Gemma 4 12b It Qat
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
Roleplay
LI
LightOnOCR 3 4B
Lightonocr · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
Vision
HE
Hermes-4-70B
Hermes · unsloth
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningRoleplayTool use
NE
Nex N2.5 Mini
Nex · bartowski
Params34.7B
Context256K
Q4_K_M22.3 GB
Vision
HO
K2-Horizon-32B
Horizon · mradermacher
Params34.8B
Context512K
Q4_K_M21.1 GB
GGUF
VI
Violet Twilight v0.2
Violet · Epiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
OR
Orion Kitchoon 26B A4B
Orion · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
AP
Apertus-8B-Instruct-2509
Apertus · unsloth
Params8.05B
Context64K
Q4_K_M5.1 GB
GGUF
QW
Qwen2.5-7B-Instruct-1M
Qwen · Mungert
Params7.6B
Context986K
Q4_K_M4.8 GB
GGUF
AP
Apex-35B-V1.0
Apex · Apexintelligence-AI
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool use
NE
NeuralLemon 7B
Neurallemon · backyardai
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GE
ThinkingCap Gemma 4 26B A4B It
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
NO
2B_or_not_2B
Not · mradermacher
Params2.5B
Context8K
Q4_K_M1.6 GB
GGUF
PR
Prompt Refine
Prompt · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
MO
Moody Krea 2 Mix V4
Moody · Henrysk
Params12.8B
Context—
Smallest2.5 GB
GGUF
QW
Qwen3-Vl-4B-Thinking
Qwen · unsloth
Params4B
Context256K
Q4_K_M2.5 GB
ReasoningVision

Other quants

Keep browsing