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
WA
WaifuGemma4 26b A4B v1
Waifugemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
GR
Granite 8b Code Base
Granite · RichardErkhov
Params8.05B
Context4K
Q4_K_M4.9 GB
Coding
LF
LFM2 24B A2B REAP
Lfm · mradermacher
Params12.4B
Context125K
Q4_K_M7.5 GB
GGUF
QW
Qwen2.5 7B Instruct Uncensored
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
PH
Borea Phi 3.5 Mini Instruct Jp
Phi · mmnga
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
OL
OLMo-1.7-7B-hf
OLMo · mradermacher
Params6.89B
Context4K
Q4_K_M4.2 GB
GGUF
MI
Dolphin3.0 Mistral 24B
Mistral · eaddario
Params23.6B
Context32K
Q4_K_M13.1 GB
GGUF
RW
rwkv 6 world 1b6
Rwkv · latestissue
Params1.6B
Context1024K
Smallest0.7 GB
GGUF
GE
Gemma 4 26B A4B StyleTune QK Heretic
Gemma · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
LL
Llama 3.1 SuperNova Lite
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
MI
bitext Mistral 7B Customer Support
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NO
Novel Humanize 4b
Novel · mradermacher
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
TO
ToolSpace 8B
Toolspace · mradermacher
Params8.19B
Context64K
Q4_K_M5.0 GB
ReasoningTool use
TI
TinyLlama-1.1B-DavidAttenborough
Tinyllama · mradermacher
Params1.1B
Context4K
Q4_K_M0.7 GB
GGUF
KO
Konstanta V4 Alpha 7B
Konstanta · mradermacher
Params7.24B
Context8K
Q4_K_M4.5 GB
Roleplay
GR
MN GRAND Gutenberg Lyra4 Lyra 12B DARKNESS
Grand · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
SE
Securecoder 30b Pro v3 Merged
Securecoder · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
LL
CodeLlama 34b Python Hf
Llama · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
GP
DMind-3
gpt-oss · Mungert
Params20.9B
Context128K
Q4_K_M16.0 GB
GGUF
QW
Qwen3.6 35B A3B Brainwaves Nex Uncensored
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
Reasoning
CO
c4ai-command-r-plus
Command R · BNK128
Params104B
Context128K
Q4_K_M62.8 GB
GGUF
MI
Huihui MiniCPM V 4.6 Thinking Abliterated
MiniCPM · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningVision
QW
SignOfFour
Qwen · mradermacher
Params34.7B
Context32K
Q4_K_M21.2 GB
CodingReasoning
MI
rana shahroz mistral 7b roleplay alpaca merge
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
QW
Qwen3.5 9B OmniCoder Claude Polaris
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingRoleplay
PH
migtissera Tess v2.5 Phi 3 medium 128k 14B
Phi · RichardErkhov
Params14B
Context128K
Q4_K_M8.6 GB
GGUF
SO
SOLAR 10.7B v1.0
Solar · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
MI
Air Striker Mixtral 8x7B ZLoss Instruct i1
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
GGUF
IN
InverseCoder-DS-6.7B
Inversecoder · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
PS
PsyMedDestroyer i1
Psymeddestroyer · mradermacher
Params20B
Context4K
Q4_K_M12.0 GB
GGUF

Other quants

Keep browsing