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
QW
Qwen3 Stargate SG1 Uncensored Abliterated 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoning
LL
Llama-3-Lumimaid-8B-v0.1-OAS
Llama · Lewdiculous
Params8B
Context8K
Q4_K_M4.9 GB
Roleplay
GE
BgGPT Gemma 2 9B IT v1.0
Gemma · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Qwen2.5 Coder 1.5B Instruct heretic
Qwen · saidutta69
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingRoleplayTool use
ZE
zen 4b i1
Zen · mradermacher
Params4.02B
Context32K
Q4_K_M2.5 GB
ReasoningTool use
RW
rwkv7 g1h 2.9b i1
Rwkv · RemySkye
Params2.95B
Context1024K
Q4_K_M2.1 GB
GGUF
LL
Llama 3.1 8B UltraMedical
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
VI
vicuna-7b-v1.5-safeunlearning
Vicuna · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
OC
OceanGPT-7b-v0.1
Oceangpt · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
LE
LeoLM hessianai 13b
Leolm · mradermacher
Params13B
Context8K
Q4_K_M7.9 GB
GGUF
MO
Moe 4x7b reason code qa i1
Moe · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
CodingReasoning
LL
Llama 3 Youko 70b Instruct
Llama · mmnga
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LF
LFM2.5 230M
Lfm · mradermacher
Params230M
Context125K
Q4_K_M0.2 GB
GGUF
QW
Qwen2-Cantonese-7B-Instruct
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
WebWorld 14B
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
LL
Deep Reasoning Llama 3.2 Dolphin3.0 3B i1
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Reasoning
LL
Llama3 8b Math Sft
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
EX
Extended-Mega-Mash-262K-8B-L3
Extended · mradermacher
Params8B
Context256K
Q4_K_M4.9 GB
GGUF
CA
CAT Thinking 8B
Cat · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Reasoning
OP
openbuddy-zero-14b-v22.3-32k
Openbuddy · mradermacher
Params14B
Context32K
Q4_K_M8.4 GB
GGUF
CO
Yi Coder 9B
Coder · mradermacher
Params8.83B
Context128K
Q4_K_M5.3 GB
Coding
NO
NovaSpark i1
Novaspark · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Roleplay
LL
Llm Jp 3 1.8b
Llm · mmnga
Params1.87B
Context4K
Q4_K_M1.2 GB
GGUF
QW
Qwen 2.5 3b RP i1
Qwen · mradermacher
Params3.4B
Context32K
Q4_K_M2.1 GB
Roleplay
ME
Meditron3 8B
Meditron · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
JA
Jais adapted 7B Reflection Tuning Natural Farmer
Jais · mradermacher
Params7B
Context4K
Q4_K_M4.3 GB
GGUF
QW
Qwable 9B Claude Fable 5 Heretic
Qwable · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
DE
DeepSeek-Coder-V2-Lite-Base
DeepSeek · legraphista
Params15.7B
Context160K
Smallest5.0 GB
Coding
MP
Mpt 7b 8k Chat
Mpt · mradermacher
Params6.65B
Context8K
Q4_K_M4.3 GB
Coding
KA
KangalKhan Alpha Rubyroid 7B
Kangalkhan · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
Tool use

Other quants

Keep browsing