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
EL
ElementalRP i1
Elementalrp · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB
Roleplay
PR
Prashna 7b
Prashna · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use
GE
Gemma 4 12B It Abliterated Uncensored
Gemma · mradermacher
Params11.9B
Context128K
Q4_K_M7.4 GB
Vision
MA
Mario Html v2 9B
Mario · bartowski
Params9.2B
Context256K
Q4_K_M6.0 GB
ReasoningTool useVision
TO
tokyotech llm Swallow 70b instruct v0.1
Tokyotech · mmnga
Params69.2B
Context4K
Q4_K_M41.5 GB
GGUF
DE
Deepseek Coder 6.7b Base
DeepSeek · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
DA
DataPilot ArrowPro 7B RobinHood
Datapilot · mmnga
Params7.24B
Context4K
Q4_K_M4.4 GB
GGUF
HO
Honey Yuzu 13B
Honey · mradermacher
Params12.5B
Context8K
Q4_K_M7.5 GB
Roleplay
MO
Mox Tiny 1
Mox · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplay
DA
DaringMaid 20B V1.1 i1
Daringmaid · mradermacher
Params20B
Context4K
Q4_K_M12.2 GB
GGUF
QW
Qwen3.5 0.8B Finetuned Lora Uncensored
Qwen · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
Vision
QW
Qwen2.5 0.5B Instruct heretic
Qwen · saidutta69
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
QW
Huihui Qwen3 VL 8B Instruct Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
DE
DeepSeek-Coder-V2-Instruct
DeepSeek · legraphista
Params236B
Context160K
Smallest47.4 GB
Coding
LL
CodeLlama 34b Instruct Hf
Llama · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
QV
QVikhr 3 4B Instruction
Qvikhr · Vikhrmodels
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
QW
Qwen2-7B-Instruct
Qwen · legraphista
Params7.62B
Context32K
Smallest1.9 GB
GGUF
LL
CodeLlama 34b Hf
Llama · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
GO
GodziLLa 30B i1
Godzilla · mradermacher
Params32.5B
Context2K
Q4_K_M19.9 GB
GGUF
MI
Mixtral AI CyberTron Ultra
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingReasoningRoleplay
OP
OpenCodeInterpreter-DS-1.3B
Opencodeinterpreter · RichardErkhov
Params1.35B
Context16K
Q4_K_M0.9 GB
GGUF
OR
Ornith 1.5 397B
Ornith · bartowski
Params397B
Context256K
Q4_K_M241.8 GB
Vision
TR
Trinity Nano Preview
Trinity · arcee-ai
Params6.12B
Context128K
Q4_K_M3.8 GB
GGUF
HE
HelpingAI-15B
Helpingai · mradermacher
Params15.3B
Context4K
Q4_K_M9.3 GB
GGUF
RA
RakutenAI-7B-instruct
Rakutenai · RichardErkhov
Params7.37B
Context32K
Q4_K_M4.5 GB
GGUF
PH
Athene Phi 3.5 mini instruct orpo
Phi · bartowski
Params3.82B
Context128K
Q4_K_M2.3 GB
GGUF
LL
Meta Llama 3.1 405B Instruct
Llama · ThomasBaruzier
Params406B
Context128K
Q4_K_M243.1 GB
Tool use
QW
Qwen2.5 32B Instruct
Qwen · ThomasBaruzier
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
QW
DMind-3-mini
Qwen · Mungert
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
MI
MiMo Ornith 9B AGSI
Mimo · bartowski
Params9.2B
Context256K
Q4_K_M6.0 GB
ReasoningTool use

Other quants

Keep browsing