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
LL
Llama 3.1 EIRAI 8B i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Meta Llama 3.1 70B Instruct
Llama · legraphista
Params70.6B
Context128K
Smallest15.3 GB
GGUF
NO
NovaSage 24B
Novasage · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
OL
OLMoE-1B-7B-0125-Instruct-Distill-ot114k-batch32
OLMo · mradermacher
Params6.9B
Context4K
Q4_K_M4.2 GB
Reasoning
FA
Falcon 11B
Falcon · mradermacher
Params11.1B
Context2K
Q4_K_M6.8 GB
GGUF
AR
arco reflection v4
Arco · mradermacher
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
DA
danube2-1.8b-Neural
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
MI
Gukbap Mistral 7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BR
Broken Tutu 24B Transgression v2.0
Broken · Naofan
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
PH
PII Model Phi3 Mini
Phi · mradermacher
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
QW
Qwen 2.5 3b Decensored
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
QW
Qwen2.5 14B Instruct
Qwen · legraphista
Params14.8B
Context32K
Smallest3.6 GB
GGUF
SM
SmolLM 135M Taiwan Instruct v1.0
SmolLM · mradermacher
Params135M
Context2K
Q4_K_M0.1 GB
GGUF
QW
Huihui Qwen3 VL 2B Thinking Abliterated
Qwen · mradermacher
Params1.72B
Context256K
Q4_K_M1.1 GB
ReasoningVision
LL
Llama 3.1 8B Lexi Uncensored V2 OBLITERATED
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
ST
Step3 VL 10B Base
Step · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Vision
BO
Bookworm 10.7B v0.4 DPO
Bookworm · RichardErkhov
Params10.8B
Context4K
Q4_K_M6.5 GB
GGUF
GP
GPT4 X Alpasta 30b
Gpt · mradermacher
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
BL
Blue-Orchid-2x7b
Blue · mradermacher
Params12.9B
Context8K
Q4_K_M7.8 GB
GGUF
JO
JoyFox-Reverie-27B
Joyfox · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
RoleplayVision
MA
Lh41 1042 Magellanic 7B 0711
Magellanic · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
LO
lobe3 i1
Lobe · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
HU
Hunyuan 7B Instruct
Hunyuan · mradermacher
Params7.5B
Context256K
Q4_K_M4.6 GB
GGUF
QW
Qwen3.5 9B RpRMax v1
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
QW
Qwen3 VL 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Vision
HU
Huihui HY MT1.5 7B Abliterated
Huihui · mradermacher
Params7.5B
Context256K
Q4_K_M4.6 GB
GGUF
HU
HuatuoGPT 3 8B
Huatuogpt · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
MI
Minecraftism 4B Uncensored
Minecraftism · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen3.8 27B Omnimerge v6
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningVision
FL
Flux Prompt Enhance
Flux · mradermacher
Params223M
Context512
Q4_K_M0.1 GB
GGUF

Other quants

Keep browsing