IQ3_XS GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 46199 models have a IQ3_XS file. Sizes run from 1M to 1030B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
PA
PaddleOCR-VL-1.6
Paddleocr · Mungert
Params467M
Context128K
Q4_K_M0.4 GB
Vision
PA
Pantheon Reasoning 27B
Pantheon · bartowski
Params27.3B
Context256K
Q4_K_M18.0 GB
ReasoningRoleplay
PY
Pythia 12b Deduped
Pythia · mradermacher
Params11.8B
Context2K
Q4_K_M7.6 GB
GGUF
WI
Wicked Stuff 26B A4B v3.0 Final
Wicked · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
XY
Xyntetik Kvist 14B
Xyntetik · mradermacher
Params14.4B
Context128K
Q4_K_M10.3 GB
Tool use
HO
K2-Horizon-3.7B
Horizon · mradermacher
Params5.06B
Context512K
Q4_K_M3.2 GB
GGUF
HU
Hunyuan 0.5B Instruct
Hunyuan · bartowski
Params539M
Context256K
Q4_K_M0.4 GB
GGUF
GR
Granite 3.1 2b Instruct
Granite · bartowski
Params2.53B
Context128K
Q4_K_M1.5 GB
GGUF
QW
Qwen3-4B-abliterated
Qwen · Mungert
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
YI
dolphin-2.9.3-Yi-1.5-34B-32k
Yi · mradermacher
Params34.4B
Context32K
Q4_K_M20.7 GB
CodingTool use
OM
Omega Arsenal 12B
Omega · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool use
PY
Pythia 410m
Pythia · mradermacher
Params405M
Context2K
Q4_K_M0.3 GB
GGUF
LL
Llama 7B rollercoaster v2 i1
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
GE
Vikhr-Gemma-2B-instruct
Gemma · Vikhrmodels
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
FI
SUFE AIFLM Lab Fin R1
Fin · bartowski
Params7.6B
Context32K
Q4_K_M4.7 GB
Reasoning
TE
Terminal RSI 27B
Terminal · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
CodingReasoningTool use
LI
LightOnOCR 3 0.8B
Lightonocr · NANI-Nithin
Params752M
Context256K
Q4_K_M0.5 GB
GGUF
PH
phi-4-mini-instruct
Phi · Mungert
Params3.84B
Context128K
Q4_K_M2.5 GB
CodingReasoning
LU
Lunar Huntress 0.1
Lunar · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayTool use
QW
Replete LLM V2.5 Qwen 14b
Qwen · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
GE
Gemma 4 31B StyleTune
Gemma · mradermacher
Params32.1B
Context256K
Q4_K_M19.5 GB
Roleplay
QW
Qwen2.5 14B
Qwen · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
WI
Wicked Stuff 26B A4B v2.1 FINAL
Wicked · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
YI
Yi 1.5 34B
Yi · RichardErkhov
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
MT
Mtreelva Dune 12B
Mtreelva · mradermacher
Params12.9B
Context256K
Q4_K_M7.9 GB
ReasoningRoleplay
SA
SaulLM 54B Instruct i1
Saullm · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
SE
SenseNova U1 8B MoT SFT
Sensenova · mradermacher
Params9.35B
Context256K
Q4_K_M5.7 GB
CodingReasoningTool use
QW
Himeros V2 27B
Qwen · Skttttt
Params27B
Context256K
Q4_K_M16.5 GB
Roleplay
GR
Kiesel v2
Granite · mradermacher
Params8.8B
Context128K
Q4_K_M5.3 GB
ReasoningTool use
LL
bangla-llama-7b-instruct-v0.1
Llama · mradermacher
Params6.89B
Context4K
Q4_K_M4.2 GB
GGUF

Other quants

Keep browsing