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
KA
Karnak
Karnak · mradermacher
Params40.7B
Context256K
Q4_K_M24.7 GB
Tool use
DE
Ph3della 14B i1
Della · mradermacher
Params14B
Context4K
Q4_K_M8.6 GB
GGUF
LO
Loopl Vl 4b
Loopl · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
Tool useVision
HO
Holo2 235B A22B
Holo · mradermacher
Params235B
Context256K
Q4_K_M142.2 GB
GGUF
EU
EuroLLM 9B MeditronFO
Eurollm · mradermacher
Params9.15B
Context4K
Q4_K_M5.6 GB
GGUF
ME
Medra27B
Medra · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
Reasoning
QW
Qwen3 30B A3B Instruct 2507 REAM Heretic
Qwen · mradermacher
Params23.3B
Context256K
Q4_K_M14.2 GB
GGUF
CY
Cydonia 24B v4.3 Heretic v3
Cydonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Coding
LL
Llama 3.1 Nemotron 70B Instruct HF abliterated i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
YI
Yi-6B-200K
Yi · duyntnet
Params6.06B
Context195K
Q4_K_M3.7 GB
GGUF
AG
L3.1 Aglow Vulca v0.1 8B i1
Aglow · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay
SA
Salience 1.5 Pro
Salience · bartowski
Params35.5B
Context256K
Q4_K_M21.9 GB
CodingReasoningTool use
NE
Nemostein 3 Hermes Omni 30b A3B
Nemostein · mradermacher
Params31.6B
Context1024K
Q4_K_M24.5 GB
ReasoningTool use
GR
MN GRAND Gutenberg Lyra4 Lyra 12B MADNESS i1
Grand · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
FA
Falcon H1 7B Instruct
Falcon · mradermacher
Params7.59B
Context256K
Q4_K_M4.6 GB
GGUF
SO
SOLAR 0 70b 16bit
Solar · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
QW
MathSmith HC Problem Synthesizer Qwen3 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
YI
blossom v3 1 yi 34b i1
Yi · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
NE
NeoHorse 1 9B Heretic
Neohorse · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
GE
Huihui gemma 4 31B it abliterated v2
Gemma · groxaxo
Params30.7B
Context—
Smallest0.0 GB
GGUF
LL
Llama 3.1 70B Instruct lorablated
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
WA
WazoCore 8B v6 Long
Wazocore · mradermacher
Params8.15B
Context128K
Q4_K_M5.0 GB
Tool use
MO
Mochi 4B
Mochi · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
GGUF
NE
NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard
Nemotron · PollardWeights
Params74B
Context256K
Smallest17.9 GB
ReasoningTool useVision
UM
Umbra v2.1 MoE 4x10.7 i1
Umbra · mradermacher
Params36B
Context32K
Q4_K_M22.0 GB
GGUF
DE
Qwen2.5 32B
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
Reasoning
MA
Mag Picaro 72B
Mag · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
Roleplay
GE
Gemma 3 12b It Vl Minimax M2.1 Heretic Uncensored Thinking
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
ReasoningVision
NE
Next 12b
Next · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Coding
MU
Muse Glimmer 30B Uncensored Heretic
Muse · mradermacher
Params27.9B
Context128K
Q4_K_M16.9 GB
GGUF

Other quants

Keep browsing