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
SP
SpydazWeb_AI_LCARS_Humanization_003
Spydazweb · mradermacher
Params7.24B
Context512K
Q4_K_M4.4 GB
Coding
QW
Qwen2.5 72B Instruct
Qwen · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
AU
AuroraRP 8x7B i1
Aurorarp · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
Roleplay
QW
Qwen2.5 7b Alpaca
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
ThinCtx Qwen3.5 0.8B
Qwen · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
GGUF
FI
FimbMoister 11Range i1
Fimbmoister · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
SE
Seed-Coder-8B-Instruct
Seed · unsloth
Params8.25B
Context32K
Q4_K_M5.1 GB
Coding
TO
TooManyMixRolePlay-7B-Story_V2
Toomanymixroleplay · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
QW
Qwen2.5 1.5B Instruct
Qwen · ThomasBaruzier
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
GL
GLM 4.5 Air
GLM · bartowski
Params110B
Context128K
Q4_K_M73.5 GB
GGUF
CO
Codex 24B Small 3.2
Codex · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
QW
Qwen3.6 40B Grand Intelligence Fable Fusion Uncensored Heretic NM DAU NEO MAX MTP
Qwen · DavidAU
Params461M
Context256K
Q4_K_M25.9 GB
CodingReasoningRoleplay
DU
dulia 13b 8k alpha i1
Dulia · mradermacher
Params13B
Context8K
Q4_K_M7.9 GB
GGUF
AY
Aya Expanse 8b
Aya · duyntnet
Params8B
Context8K
Q4_K_M5.1 GB
GGUF
TE
TerminalHorizon 27B
Terminalhorizon · bartowski
Params27B
Context256K
Q4_K_M17.2 GB
Vision
MP
Mpt 7b 8k
Mpt · mradermacher
Params6.65B
Context8K
Q4_K_M4.3 GB
GGUF
HO
K2-Horizon-7B
Horizon · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
GGUF
ST
Starcoder2 3b
StarCoder · mradermacher
Params3.03B
Context16K
Q4_K_M1.9 GB
Coding
DE
Deepseek Coder 7b Instruct v1.5
DeepSeek · mradermacher
Params6.91B
Context4K
Q4_K_M4.2 GB
Coding
MA
MAI Gym 9B
Mai · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
CA
CalibForge 35B A3B
Calibforge · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
QW
ThinCtx Qwen3.5 2B
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
GGUF
AC
ActIO-UI-7B-RLVR
Actio · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
LB
LBS 27B
Lbs · bartowski
Params26.9B
Context256K
Q4_K_M17.2 GB
ReasoningTool useVision
HO
K2 Horizon 7B UnrealEngine
Horizon · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
CodingReasoningTool use
GE
Gemma 4 26B A4B It Uncensored Heretic
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
QW
Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Reasoning
DE
Deepseek-V3.1-Terminus
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M405.4 GB
GGUF
PR
Bu 30b A3B Preview
Preview · bartowski
Params30.5B
Context256K
Q4_K_M18.6 GB
Vision
LI
Ling 3.0 Flash Sante
Ling · bartowski
Params127B
Context256K
Q4_K_M80.4 GB
ReasoningTool use

Other quants

Keep browsing