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
DA
L3 DARKEST PLANET 16.5B i1
Darkest · mradermacher
Params16.5B
Context8K
Q4_K_M10.0 GB
Roleplay
EG
Ege 8b 1.1
Ege · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
NA
Nanbeige4.1-3B
Nanbeige · Mungert
Params3.93B
Context256K
Q4_K_M2.6 GB
GGUF
QW
Qwen3.8 Queen 27B
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Roleplay
LL
Llama 3.1 70B Japanese Instruct 2407
Llama · mmnga
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
KE
Keural Cortex 8B v1.0 1
Keural · mradermacher
Params8.19B
Context64K
Q4_K_M5.0 GB
Tool use
QW
Huihui Qwen3 Coder Next Opus 4.6 Reasoning Distilled Abliterated
Qwen · mradermacher
Params79.7B
Context256K
Q4_K_M48.5 GB
CodingReasoningTool use
ED
EdgeRunner Command Nested
Edgerunner · mradermacher
Params7.6B
Context32K
Q4_K_M4.7 GB
GGUF
ZE
Zephyr 7b Beta Abliterated
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen35B Agent R2 Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
KL
Klyrune 2B General
Klyrune · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
ReasoningTool use
MI
Mistral NeuralDPO
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
BO
Borealis Open 1b
Borealis · mradermacher
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
LL
alfredplpl Llama 3 8B Instruct Ja
Llama · mmnga
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
OL
Olmo 3 7B Think
OLMo · mradermacher
Params7.3B
Context64K
Q4_K_M4.5 GB
Reasoning
SW
Swallow-13b-hf
Swallow · mradermacher
Params13.1B
Context4K
Q4_K_M7.9 GB
GGUF
QW
Zhi Create Qwen3 32B
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
Reasoning
QW
Qwen3.5 122B A10B Abliterated
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
GGUF
CO
Yi Coder 9B
Coder · mradermacher
Params8.83B
Context128K
Q4_K_M5.3 GB
Coding
LL
Llama-3-Groq-70B-Tool-Use
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
Tool use
ZE
zephyr 7b alpha
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
EL
Elysium2.1-11b
Elysium · mradermacher
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
MO
MOSS Image Text Encoder Heretic
Moss · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
CodingReasoningTool use
KI
Kimi Linear REAP 35B A3B Instruct i1
Kimi · mradermacher
Params35B
Context1024K
Q4_K_M21.3 GB
GGUF
YI
Yi-9B-200K
Yi · mradermacher
Params8.83B
Context256K
Q4_K_M5.3 GB
GGUF
EI
Einstein-v4-7B
Einstein · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingTool use
GE
Gemma 3 12b It Vl HighIQ Polaris Heretic Uncensored Thinking
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
ReasoningVision
ST
L3-8B-Stheno-v3.2
Stheno · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Emma 500 Llama2 7b
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
KA
Kairos
Kairos · mradermacher
Params8.2B
Context32K
Q4_K_M5.0 GB
GGUF

Other quants

Keep browsing