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 32B VL GLM 4.7 Flash HI16 Heretic Uncensored Thinking
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
ReasoningRoleplayVision
OL
OLMoE 1B 7B 0924 Instruct
OLMo · mradermacher
Params6.9B
Context4K
Q4_K_M4.2 GB
GGUF
QW
Qwen3.5 27B Abliterated Ko
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
GR
Granite 3b Code Instruct 2k
Granite · mradermacher
Params3.48B
Context2K
Q4_K_M2.1 GB
CodingTool use
GR
Granite 3.2 8b Instruct
Granite · bartowski
Params8.17B
Context128K
Q4_K_M4.9 GB
GGUF
BE
berkeley nest Starling LM 7B alpha
Berkeley · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
FU
FusionNet_7Bx2_MoE_14B
Fusionnet · mradermacher
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
DA
Darwin 4B Chimera
Darwin · bartowski
Params4B
Context40K
Q4_K_M2.6 GB
Reasoning
PY
Pythia 6.9b
Pythia · mradermacher
Params6.86B
Context2K
Q4_K_M4.4 GB
GGUF
LL
DarkIdol Llama 3.1 8B Instruct 1.0 Uncensored i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay
MI
Ministral 3 14B Instruct 2512 Absolute Heresy
Mistral · mradermacher
Params13.5B
Context256K
Q4_K_M8.2 GB
GGUF
NO
Novaeus Promptist 7B Instruct i1
Novaeus · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
MO
MoNeuTrix MoE 4x7B i1
Moneutrix · mradermacher
Params24.2B
Context32K
Q4_K_M14.8 GB
GGUF
IR
Irene-RP-v2-7B_128k
Irene · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
LL
Llama 3.2 1B Instruct
Llama · legraphista
Params1.24B
Context128K
Smallest0.4 GB
GGUF
LE
LemonKunoichiWizardV3
Lemonkunoichiwizardv · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
QW
Qwen2.5 7B
Qwen · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
Roleplay
DW
Dwight 4b
Dwight · bartowski
Params4B
Context256K
Q4_K_M2.6 GB
GGUF
QW
Qwen2.5-3B-Instruct
Qwen · Mungert
Params3.1B
Context32K
Q4_K_M1.9 GB
GGUF
LL
Llama Leonida v2
Llama · mradermacher
Params8.2B
Context128K
Q4_K_M5.0 GB
GGUF
WI
winter garden 7b delta
Winter · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
SZ
SzilviaB Daredevil LongWriter 8B abliterated i1
Szilviab · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 32B VL Instruct Polaris HI16 Heretic Uncensored
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
RoleplayVision
DE
Qwen3 8B DeepSeek v3.2 Speciale Distill
DeepSeek · TeichAI
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
MI
Mahou-1.2-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
RA RFT Qwen2.5 VL 7B
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
LF
LFM2.5 350M RLCD
Lfm · NANI-Nithin
Params354M
Context125K
Q4_K_M0.2 GB
GGUF
YI
01 ai Yi 9B 200K
Yi · RichardErkhov
Params8.83B
Context256K
Q4_K_M5.3 GB
GGUF
QW
online-dpo-qwen2-4
Qwen · RichardErkhov
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
QW
ColdBrew Qwen3.5 CharThink Base
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use

Other quants

Keep browsing