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
PY
Pythia 1b Deduped
Pythia · mradermacher
Params1.01B
Context2K
Q4_K_M0.7 GB
GGUF
QW
Qwen3.8 Flash Next REAM 60Pct
Qwen · mradermacher
Params129B
Context256K
Q4_K_M87.0 GB
GGUF
GE
Gemma 4 E2B It Anon Reasoning
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool use
YI
CaPlatTessDolXaBoros Yi 34B 200K DARE Ties HighDensity
Yi · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
LL
Collaiborator MEDLLM Llama 3 8B v1 i1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 4B Abliterated TIES
Qwen · mradermacher
Params4.02B
Context32K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen3.5 13B Deckard Heretic Uncensored Thinking
Qwen · mradermacher
Params12.4B
Context256K
Q4_K_M7.7 GB
ReasoningRoleplay
EV
L3-8B-Everything-COT
Everything · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
CA
Captain Eris Diogenes Twilight V0.420 12B GGUF ARM Imatrix
Captain · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
MI
mistralai Mistral 7B Instruct v0.2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
MiniMA-2-1B
Minima · mradermacher
Params1.37B
Context4K
Q4_K_M0.8 GB
GGUF
LL
Waktaverse Llama 3 KO 8B Instruct
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LE
Lexi Coder v5.1
Lexi · mradermacher
Params7.25B
Context32K
Q4_K_M4.4 GB
Coding
GE
Gemma 4 Gemsicle 31B
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
PS
PsyMedLewdReMM Inverted 20B
Psymedlewdremm · mradermacher
Params20B
Context4K
Q4_K_M12.0 GB
GGUF
LL
llama-3-tulu-2-8b
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
GR
Granite 4.0 H Tiny
Granite · mradermacher
Params6.94B
Context1024K
Q4_K_M4.2 GB
GGUF
WA
Wayfarer 2 12B Absolute Heresy
Wayfarer · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
ST
L3-8B-Stheno-v3.2-abliterated
Stheno · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
GP
Gpt Oss 20b
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · ThomasBaruzier
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
SM
Smart Commit 1.5b v0.3
Smart · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
KL
Klyrune 2B Coder
Klyrune · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingReasoningTool use
MI
Mistral 7B Instruct v0.2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SI
SIREN 3B
Siren · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
SM
SmolLM 360M
SmolLM · mradermacher
Params362M
Context2K
Q4_K_M0.3 GB
GGUF
RO
Roleplay 9B lora 800 porn i1
Roleplay · mradermacher
Params8.83B
Context16K
Q4_K_M5.3 GB
Roleplay
GE
Gemma 4 12B It Uncensored Opus4.7 Cot
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
SM
SmolLM 135M Instruct
SmolLM · mradermacher
Params135M
Context2K
Q4_K_M0.1 GB
Tool use
NE
Nemo Gutenberg 12b v1
Nemo · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF

Other quants

Keep browsing