IQ3_S GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 45340 models have a IQ3_S file. Sizes run from 1M to 1030B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
ReSearch Qwen 7B Instruct
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
JI
JiRackUltra_14b
Jirackultra · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
AT
Athena-CodePhi-7B-4k-v0.1
Athena · mradermacher
Params3.82B
Context4K
Q4_K_M2.3 GB
Coding
GE
lei HuggingFace Gemma 2 9B 4bit Chat Level Measurement Guide 07242024
Gemma · RichardErkhov
Params3.4B
Context—
Q4_K_M1.7 GB
GGUF
ST
Starcoderbase
StarCoder · mradermacher
Params15.8B
Context8K
Q4_K_M10.1 GB
Coding
QW
Qwen3 Yoyo V4 42B A3B Thinking TOTAL RECALL
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
CodingReasoning
QW
Katy 27B
Qwen · sirfyyn
Params1.92B
Context256K
Smallest0.0 GB
GGUF
NE
NeuralGanesha 7b
Neuralganesha · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
SP
Spark X2.6 4B Tema_Q Abliterated
Spark · mradermacher
Params4.11B
Context1024K
Q4_K_M2.6 GB
ReasoningTool use
GE
Gemma 4 12B It QAT SOMPOA Heresy
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
LF
Lfm25 24b
Lfm · PollardWeights
Params24B
Context128K
Smallest5.8 GB
GGUF
GE
Gemma 4 E4B It Erotica
Gemma · mradermacher
Params7.5B
Context128K
Q4_K_M5.3 GB
GGUF
LL
Llama 3.1 Storm 8B
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
MI
Mistral Military 24B
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
OR
Orca 2 13b
Orca · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
JA
Javi0.3 4B
Javi · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
ReasoningTool use
QW
Qwen3 Psychological Reasoning 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Reasoning
DR
Draco 8x7B
Draco · mradermacher
Params46.7B
Context8K
Q4_K_M28.6 GB
Tool use
QW
BiggerCoQ Qwen3 10b
Qwen · mradermacher
Params10.9B
Context40K
Q4_K_M6.6 GB
GGUF
AT
Athena-CodeZephyr-7B-v0.2
Athena · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
MI
Hermes-2-Pro-Mistral-7B-infinity
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
QW
Qwen3.5-35B-A3B
Qwen · Mungert
Params34.7B
Context256K
Q4_K_M21.6 GB
Vision
GR
Parable Granite 4.1 3B Claude Fable 5 heretic
Granite · saidutta69
Params3.4B
Context128K
Q4_K_M2.1 GB
ReasoningTool use
QW
Qwimi 4B
Qwimi · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
Tool use
VI
MN Violet Lotus 12B
Violet · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
GE
Gemma 4 MoonGem 31B
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
ZE
ZeusLabs Chronos Divergence 33B
Zeuslabs · RichardErkhov
Params32.5B
Context16K
Q4_K_M19.6 GB
GGUF
HE
HERETICSEEK 7B Ditill
Hereticseek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
TH
TherapyLlama 8B v1 i1
Therapyllama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
NU
Nu 17b
mradermacher
Params16.8B
Context32K
Q4_K_M10.3 GB
Roleplay

Other quants

Keep browsing