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
QW
Qwen3.5 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
LI
Ling 3.0 Flash Fin
Ling · bartowski
Params127B
Context256K
Q4_K_M77.8 GB
Tool use
QW
Qwen2.5 3B Instruct
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
HE
Hermes 4.3 36B
Hermes · bartowski
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningRoleplayTool use
GP
Gpt2 Medium
Gpt · mradermacher
Params406M
Context1K
Q4_K_M0.3 GB
GGUF
GE
Gemma 4 26b A4B Heretic
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
LE
LensVLM 9B
Lensvlm · bartowski
Params8.95B
Context256K
Q4_K_M5.8 GB
Vision
RU
Rumeni 26B A4B
Rumeni · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
HA
HarmonicHarlequin v5 20B i1
Harmonicharlequin · mradermacher
Params33.3B
Context4K
Q4_K_M20.1 GB
GGUF
HO
K2-Horizon-3.7B
Horizon · bartowski
Params5.06B
Context512K
Q4_K_M3.3 GB
GGUF
SW
Swish 26B A4B
Swish · ReadyArt
Params25.2B
Context256K
Q4_K_M17.7 GB
Roleplay
CO
C4Ai Command R Plus 08 2024
Command R · legraphista
Params104B
Context128K
Smallest23.2 GB
GGUF
MI
Ministral 3 8B Reasoning UNCENSORED Heretic
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
Reasoning
GR
Granite 20b Code Instruct R1.1
Granite · RichardErkhov
Params20B
Context8K
Q4_K_M12.8 GB
CodingReasoning
BA
bagel dpo 34b v0.5 i1
Bagel · mradermacher
Params34.4B
Context195K
Q4_K_M21.2 GB
CodingRoleplayTool use
GE
Gemma 4 Dark Thoughts 31B
Gemma · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
RoleplayVision
FA
Falcon 11B
Falcon · mradermacher
Params11.1B
Context2K
Q4_K_M6.8 GB
GGUF
PH
Phi 3 Medium 4k Instruct
Phi · bartowski
Params14B
Context4K
Q4_K_M8.6 GB
Coding
GE
Gemma 4 31B StyleTune Heretic Ara
Gemma · mradermacher
Params32.1B
Context256K
Q4_K_M19.5 GB
Roleplay
MI
Ministral 3 8B Claude Opus Reasoning Distilled
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
Reasoning
QW
Qwen2-0.5B
Qwen · legraphista
Params494M
Context128K
Smallest0.3 GB
GGUF
MU
Muse Glimmer 30B Heretic
Muse · bartowski
Params27.9B
Context128K
Q4_K_M17.3 GB
Vision
MU
Muse Glimmer 30B Esper4
Muse · bartowski
Params27.9B
Context128K
Q4_K_M17.3 GB
CodingReasoningVision
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
DE
uncensoredai UncensoredLM DeepSeek R1 Distill Qwen 14B
DeepSeek · bartowski
Params14.2B
Context128K
Q4_K_M8.6 GB
Reasoning
QW
Qwen3.8 27B Cold Fusion GAIN Heretic
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
FE
Fenrir X 26B A4B
Fenrir · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
AM
Amaretto 14B
Amaretto · mradermacher
Params13.5B
Context256K
Q4_K_M8.2 GB
Tool use
QW
Qwen3.5 4B Claude 3xMerge Jackrong UNCENSORED Heretic
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
CY
Cyber Tiel Coder 35B A3B MTP TTQ
Cyber · TokenTinkerer
Params35.5B
Context256K
Q4_K_M21.6 GB
CodingReasoningTool use

Other quants

Keep browsing