IQ2_XS GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 26336 models have a IQ2_XS file. Sizes run from 2M to 2450B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
OrionStar-Yi-34B-Chat-Llama
Llama · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
CY
Cydonia 24B v4.2.0
Cydonia · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
MI
Mistral Small 24B Instruct 2501
Mistral · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
QW
Huihui Qwen3.6 27B Abliterated
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
DA
Darwin 36B Opus
Darwin · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Reasoning
NE
Nemotron 3 Nano 30B A3B
Nemotron · bartowski
Params31.6B
Context1024K
Q4_K_M24.7 GB
Coding
OL
Olmo 3.1 32B Instruct
OLMo · bartowski
Params32.2B
Context64K
Q4_K_M19.5 GB
GGUF
GE
Gemma 4 MoonGem 31B
Gemma · bartowski
Params30.7B
Context256K
Q4_K_M19.5 GB
RoleplayVision
PR
PreciseCoder 9B
Precisecoder · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Coding
CY
Cyberdonia 24B v8
Cyberdonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
WI
Wicked Stuff 26B A4B v2.0 Final
Wicked · ReadyArt
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
QW
Qwen3.6 27B Architect Polaris2 Fable B F451 heretic
Qwen · mcgonzo
Params27B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen3.8-27B
Qwen · NilVoid
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
QW
Huihui Qwen3 Next 80B A3B Thinking Abliterated
Qwen · mradermacher
Params80B
Context256K
Q4_K_M48.4 GB
Reasoning
VE
Veloxy Flash 15B
Veloxy · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
LL
Meta Llama 3 70B Instruct
Llama · MaziyarPanahi
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
YI
Yi-1.5-6B-Chat
Yi · bartowski
Params6.06B
Context4K
Q4_K_M3.7 GB
GGUF
TE
Tev 27B
Tev · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
VI
Vinci MLE 123B 1.0
Vinci · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
CodingTool use
LL
Llama 3.2 3B Instruct
Llama · DavidAU
Params3.21B
Context128K
Q4_K_M2.0 GB
Roleplay
QW
Huihui Qwen3 Coder Next Abliterated
Qwen · mradermacher
Params79.7B
Context256K
Q4_K_M48.5 GB
Coding
OL
OLMoE 1B 7B 0924 Instruct
OLMo · mradermacher
Params6.9B
Context4K
Q4_K_M4.2 GB
GGUF
QW
Qwen3.8-27B
Qwen · ahmed-amedo
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
CY
Cydonia 24B v4.3 Absolute Heresy
Cydonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
NE
nexus legal
Nexus · King3Djbl
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
Qwen2.5 VL 32B Instruct
Qwen · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
Vision
GE
Wicked Stuff 31B Final
Gemma · ReadyArt
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayTool use
MO
Moonlight 16B A3B Instruct
Moonlight · mmnga
Params16B
Context8K
Q4_K_M10.5 GB
GGUF
QW
Qwen2.5-VL-7B-Instruct
Qwen · Mungert
Params7.6B
Context125K
Q4_K_M4.8 GB
Vision
QW
Qwen3.8 27B Heretic Abliterated Uncensored
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF

Other quants

Keep browsing