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
AU
AuroraCap 7B IMG xtuner i1
Auroracap · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
YO
Yousei-22B
Yousei · mradermacher
Params21.8B
Context4K
Q4_K_M13.2 GB
GGUF
LL
llama-3-70B-Instruct-abliterated
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
MI
Mistral Small 3.2 24B Instruct 2506 Absolute Heresy
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
YI
Yi-34B-Chat
Yi · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
NE
Dory1.0 4B BF16 Llamacpp
Nemotron · cloudnathan5
Params3.98B
Context256K
Q4_K_M2.4 GB
GGUF
BA
Basal Omni 1.0 Ultra
Basal · bartowski
Params30.7B
Context256K
Q4_K_M19.5 GB
Vision
QW
Qwen2.5 32B Instruct Abliterated
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
MY
MythoMax L2 13b i1
Mythomax · mradermacher
Params13B
Context4K
Q4_K_M8.1 GB
GGUF
QW
Qwen2.5 7B Instruct Abliterated v2
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
MI
Dolphin-Mistral-24B-Venice-Edition
Mistral · Mungert
Params23.6B
Context32K
Q4_K_M14.5 GB
GGUF
DE
DeepSeek R1 0528 Qwen3 8B Heretic
DeepSeek · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning
LL
llm jp 3.1 13b instruct4
Llm · mmnga
Params13.7B
Context4K
Q4_K_M8.3 GB
GGUF
QW
OpenSpatial Qwen2.5 VL 7B
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
ReasoningVision
KE
cognition ai Kevin 32B
Kevin · bartowski
Params32.8B
Context40K
Q4_K_M19.9 GB
GGUF
LF
LFM2 12B A1B SpeedDemon The Deckard II HERETIC Uncensored
Lfm · mradermacher
Params11.3B
Context125K
Q4_K_M6.8 GB
CodingRoleplay
GL
GLM 4 32B Base 32K
GLM · bartowski
Params32.6B
Context32K
Q4_K_M19.7 GB
GGUF
SH
Shisutemu Masuta Q3 32B
Shisutemu · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
LL
llama-3-sqlcoder-8b
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
Coding
QW
Qwen2.5 14B
Qwen · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
ET
Eternal.Bondange 3.2 1B
Eternal · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
Tool use
LL
Llama 3.1 8B xLAM Agent
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Tool use
TH
TheSpice-7b-FT-v0.3.1
Thespice · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen2.5 72B Instruct Malaysian
Qwen · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
ST
MN Starlight Sylph 12B
Starlight · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
DE
DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO IQ2 XXS MXFP8 Engram
DeepSeek · Starw1
Params197B
Context1024K
Smallest138.6 GB
GGUF
GE
Gemma4 E4B Mahou Nsfw
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
Roleplay
QW
Qwen3.5 9B GLM5.1 Distill v1
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Reasoning
SC
ScienceRSI 8b
Sciencersi · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
JU
juanako 7b UNA i1
Juanako · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

Other quants

Keep browsing