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
CH
CarbonGPT
Chat · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
QW
ThinkLite Critic 7b
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
ReasoningVision
QW
NQLSG Qwen2.5 14B MegaFusion v5 Roleplay
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Roleplay
QW
Qwen3 1.7B heretic
Qwen · saidutta69
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
SL
Slimaki 24B v1
Slimaki · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
MI
Nous-Hermes-2-Mixtral-8x7B-DPO
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB
Tool use
PS
Psyfighter2 13B Vore
Psyfighter · RichardErkhov
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
SE
Seed OSS 36B Base
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
MI
Devstral Small 2 24B Instruct Abliterated
Mistral · mradermacher
Params23.6B
Context384K
Q4_K_M14.3 GB
Coding
LL
llama-3-tulu-2-dpo-8b
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
PO
Polar 32B
Polar · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
LL
liberalis-cogitator-llama-3.1-8b-dpo
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay
KR
Kreatix K1
Kreatix · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
NE
neural chat 7b v3 3
Neural · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OL
Olmo 3 7B Instruct SFT
OLMo · mradermacher
Params7.3B
Context64K
Q4_K_M4.5 GB
Tool use
SM
SmolLM 135M GrammarSFT
SmolLM · mradermacher
Params135M
Context2K
Q4_K_M0.1 GB
GGUF
MI
Nous-Hermes-2-Mixtral-8x7B-SFT
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB
Tool use
LL
llama 2 7b chat sexed version3
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.2 GB
GGUF
QW
Qwen3 14B Base
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
AI
airoboros l2 70b 2.2
Airoboros · mradermacher
Params69B
Context4K
Q4_K_M41.7 GB
GGUF
LL
llm-compiler-7b-ftd
Llm · legraphista
Params6.74B
Context16K
Smallest1.5 GB
GGUF
LL
Llama 3.1 8B Instruct Jbliterated v2
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
TE
Terminal RSI 27B
Terminal · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
SO
SorcererLM 8x22b iMat
Sorcererlm · Quant-Cartel
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
HU
Huihui4 48B A4B Abliterated
Huihui · mradermacher
Params48B
Context256K
Q4_K_M32.0 GB
GGUF
MI
Mistral Small 24B Instruct 2501 Abliterated
Mistral · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
QW
Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B
Qwen · mradermacher
Params19B
Context32K
Q4_K_M11.6 GB
Coding
IN
AlchemistCoder-DS-6.7B
InternLM · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
Qwable 9B Claude Fable 5 OBLITERATED
Qwable · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
CO
Codegeex4 All 9b
Codegeex · mradermacher
Params9.4B
Context128K
Q4_K_M6.3 GB
GGUF

Other quants

Keep browsing