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.
LL
Fireball Alpaca Llama3.1.08 8B C R1 KTO Relection i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
LL
Llama 3.1 8B toxic dpo NoWarning i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
QW
Qwen3.5 27B Claude 4.6 OS INSTRUCT
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GE
Gemma 4 A4B 98e v5 Coder It
Gemma · mradermacher
Params19.9B
Context256K
Q4_K_M13.2 GB
AV
Avenger2.01-xb-Passthrough
Avenger · mradermacher
Params12.3B
Context32K
Q4_K_M7.4 GB
GR
Granite 4.2 30b
Granite · mradermacher
Params29.3B
Context128K
Q4_K_M17.7 GB
WI
winter garden 7b beta
Winter · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
VI
Vicuna 7b v1.3
Vicuna · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
CO
c4ai-command-r-plus
Command R · pmysl
Params104B
Context128K
Q4_K_M62.8 GB
LL
kykim0 Llama 2 7b ultrachat code
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
NE
NEIRA HF1 4B
Neira · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
QW
Qwen3.6 27B Tachibana Agent
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
OL
OLMoE 1B 7B 0924 SFT
OLMo · mradermacher
Params6.9B
Context4K
Q4_K_M4.2 GB
QW
Qwen2.5 1.5B Instruct
Qwen · legraphista
Params1.54B
Context32K
Smallest0.4 GB
QW
Qwen3 33B A3B Quad Mind
Qwen · mradermacher
Params33B
Context32K
Q4_K_M20.1 GB
EM
EmertonOgno-7B
Emertonogno · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
PH
Phi4.React.Turn.V2.Full i1
Phi · mradermacher
Params14.7B
Context16K
Q4_K_M8.9 GB
WI
Wicked Tutu 26B A4B
Wicked · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
QW
Huihui Qwen3 VL 32B Instruct Abliterated
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
GE
Gemma 4 31B It Scotoma 2
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
VU
VulnLLM R 7B
Vulnllm · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
OH
Ohm MythosNano
Ohm · mradermacher
Params3.09B
Context128K
Q4_K_M1.9 GB
LO
LoomAI
Loomai · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
PA
Palmyra-Med-70B
Palmyra · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
MI
bophades mistral truthy DPO 7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
LZ
lzlv limarpv3 l2 70b i1
Lzlv · mradermacher
Params69B
Context4K
Q4_K_M41.7 GB
LF
LFM2.5 Encoder 350M
Lfm · mradermacher
Params354M
Context125K
Q4_K_M0.2 GB
QW
Qwen3.5 4B Deckard HERETIC UNCENSORED Thinking
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
SE
Seamaiiza-7B-v2-128k
Seamaiiza · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GW
gWorld 8B
Gworld · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB