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
GO
Goetia 24B v1.4 Heretic
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
TO
ToolSpace 35B A3B
Toolspace · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
CO
C4Ai Command R v01
Command R · mradermacher
Params35B
Context128K
Q4_K_M21.5 GB
GGUF
QW
Qwen2.5 3B
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
QW
ColdBrew Qwen3.5 RP_Base CharThink
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningRoleplayTool use
MI
YuisekinAIEvol Mistral 7B ja math v0.1.1
Mistral · mmnga
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
WO
WorldSim Opus 3.6 35B A3B
Worldsim · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
ReasoningRoleplayVision
EX
EXAONE 3.5 7.8B Instruct
Exaone · ThomasBaruzier
Params7.8B
Context32K
Q4_K_M4.8 GB
GGUF
QW
ThinCtx Qwen3.5 4B
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
D3
d3 i1
mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Vision
FR
Free_Sydney_13b_HF
Free · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
QW
QVQ 72B Preview
Qwen · bartowski
Params72.7B
Context125K
Q4_K_M47.4 GB
Vision
LL
Llama 3.1 Nemotron 70B Instruct HF
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
NE
NVIDIA Nemotron 3.5 Lightning 30B A3B
Nemotron · NANI-Nithin
Params32.9B
Context1024K
Q4_K_M25.4 GB
GGUF
HU
Huozi3.5
Huozi · mradermacher
Params46.9B
Context32K
Q4_K_M28.6 GB
GGUF
NA
Nanbeige 4.3 33B Heretic
Nanbeige · Luni
Params33.1B
Context512K
Smallest7.7 GB
ReasoningTool use
LL
CodeLlama 13b Hf
Llama · mradermacher
Params13B
Context16K
Q4_K_M7.9 GB
Coding
FR
FrogNano 4B 2609 Heretic
Frognano · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
NO
Noema 1.5 4B Deep
Noema · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoning
QW
Qwen3.5 4B Anon Reasoning v2
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
OR
Ornith 1.0 35B Uncensored Heretic
Ornith · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
PY
Pythia 160m Deduped
Pythia · mradermacher
Params162M
Context2K
Q4_K_M0.1 GB
GGUF
SU
SummLlama3.1 8B
Summllama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
FU
Fugaku-LLM-13B-instruct
Fugaku · mmnga
Params13.4B
Context2K
Q4_K_M9.6 GB
GGUF
LL
Llama 3.2 1B Instruct Abliterated
Llama · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
GGUF
SK
Sky T1 32B Preview
Sky · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
LL
Llm Jp 3 3.7b
Llm · mmnga
Params3.78B
Context4K
Q4_K_M2.3 GB
GGUF
AP
Apertus 70B Instruct 2509 Abliterated
Apertus · mradermacher
Params70.6B
Context64K
Q4_K_M43.7 GB
GGUF
PH
Phi 4 Reasoning plus_Nemotron Reasoning 0803_SFT GRPO
Phi · mradermacher
Params14.7B
Context32K
Q4_K_M9.1 GB
Reasoning
IN
InternLM2
InternLM · legraphista
Params1.89B
Context8K
Smallest0.5 GB
GGUF

Other quants

Keep browsing