IQ2_S GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 26079 models have a IQ2_S file. Sizes run from 2M to 1030B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2.5 14B Instruct
Qwen · legraphista
Params14.8B
Context32K
Smallest3.6 GB
GGUF
KI
Kimi Dev 72B
Kimi · bartowski
Params72.7B
Context128K
Smallest23.7 GB
GGUF
QW
Huihui Qwen3 VL 2B Thinking Abliterated
Qwen · mradermacher
Params1.72B
Context256K
Q4_K_M1.1 GB
ReasoningVision
LL
Llama 3.1 8B Lexi Uncensored V2 OBLITERATED
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
ST
Step3 VL 10B Base
Step · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Vision
MA
Magnum v4 22b
Magnum · bartowski
Params22.2B
Context32K
Q4_K_M13.3 GB
GGUF
MA
Lh41 1042 Magellanic 7B 0711
Magellanic · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
LO
lobe3 i1
Lobe · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
HU
Hunyuan 7B Instruct
Hunyuan · mradermacher
Params7.5B
Context256K
Q4_K_M4.6 GB
GGUF
QW
Qwen3.5 9B RpRMax v1
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
QW
Qwen3 VL 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Vision
HU
Huihui HY MT1.5 7B Abliterated
Huihui · mradermacher
Params7.5B
Context256K
Q4_K_M4.6 GB
GGUF
HU
HuatuoGPT 3 8B
Huatuogpt · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
MI
Minecraftism 4B Uncensored
Minecraftism · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen3 8B 64k Josiefied Uncensored NEO Max
Qwen · DavidAU
Params8.19B
Context64K
Q4_K_M5.8 GB
ReasoningRoleplay
QW
Qwen2.5 14B
Qwen · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
Roleplay
QW
VulnLLM-R-7B
Qwen · Mungert
Params7.6B
Context32K
Q4_K_M4.9 GB
CodingReasoning
AQ
Aquif Grounding 7B
Aquif · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
CY
Cydonia 22B v1
Cydonia · bartowski
Params22.2B
Context128K
Q4_K_M13.3 GB
GGUF
CO
codegemma-2b
Codegemma · bartowski
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
UG
L3-8B-UGI-DontPlanToEnd-test
Ugi · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 7B Instruct 1M Thinking Claude Gemini GPT5.2 DISTILL PaperWitch Heresy
Qwen · mradermacher
Params7.62B
Context986K
Q4_K_M4.7 GB
ReasoningRoleplay
QW
Qwen2.5 8x7B Vee Eight Coder Instruct 53B
Qwen · mradermacher
Params53.2B
Context32K
Q4_K_M32.4 GB
CodingTool use
KR
KrakenSakura Maelstrom 12B v1
Krakensakura · Naphula
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
MO
MotherEarth_1.0
Motherearth · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
Roleplay
LL
Fireball Llama 3.1 8B Philos Reflection v0.3 i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 VL 12B Thinking Brainstorm20x
Qwen · mradermacher
Params11.9B
Context256K
Q4_K_M7.2 GB
CodingReasoningVision
SA
Sarashina2.2 1b Instruct v0.1
Sarashina · mmnga
Params1.41B
Context8K
Q4_K_M0.9 GB
GGUF
XL
xLAM 8x7b R
Xlam · bartowski
Params46.7B
Context32K
Q4_K_M28.4 GB
Tool use
CA
Calme-7B-Instruct-v0.1.1
Calme · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use

Other quants

Keep browsing