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
NU
NuMarkdown-8B-Thinking
Numarkdown · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
ReasoningVision
LL
dolphin-2.9.1-llama-3-70b
Llama · legraphista
Params70.6B
Context8K
Smallest15.3 GB
CodingTool use
PA
PathfinderAI5.0 i1
Pathfinderai · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
ReasoningTool use
LL
dolphin 2.9 llama3 70b GGUF smashed
Llama · PrunaAI
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
TH
TherapyBeagle 11B v2 i1
Therapybeagle · mradermacher
Params10.7B
Context32K
Q4_K_M6.5 GB
GGUF
NE
NeuralMaths Experiment 7b
Neuralmaths · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
MI
internlm2-math-plus-mixtral8x22b
Mistral · legraphista
Params141B
Context64K
Smallest29.6 GB
GGUF
YI
Yi-34B-200K-AEZAKMI-v2
Yi · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
NE
Next 8b
Next · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning
GR
Grok Oss Thanatos
Grok · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
IN
Index Translate 35B A3B Preview
Index · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
GGUF
QW
Qwen3.5 9B Claude 4.6 Opus Deckard V4.2 Uncensored Heretic Thinking
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningRoleplay
MI
K2S3 Mistral 7bx2 48layers_v1.2
Mistral · RichardErkhov
Params10.9B
Context32K
Q4_K_M6.6 GB
GGUF
EX
Experiment26 7B
Experiment · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen2.5 0.5B Instruct 3MPER0RR Abliterated
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
LL
Llama 2 7b Chat Hf
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
QW
Qwen3.5 35B A3B Heretic Opus 4.6 Distilled
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
Qwen3 42B A3B Spock Brutal Recall Instruct
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
CodingReasoning
KA
karakuri lm 8x7b chat v0.1
Karakuri · mmnga
Params46.7B
Context32K
Smallest9.8 GB
GGUF
ZE
zephyr 7b hh dpo
Zephyr · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 42B A3B 2507 Thinking Abliterated Uncensored TOTAL RECALL v2 Medium MASTER CODER
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
CodingReasoning
DE
DeepSeek R1 Distill Qwen 32B Uncensored
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.8 GB
Reasoning
GE
Gemma-2-9B-It-SPPO-Iter3
Gemma · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
YI
Yi-1.5-9B-32K
Yi · mradermacher
Params8.83B
Context32K
Q4_K_M5.3 GB
GGUF
MI
Dolphin Mistral 24B Venice Edition Heretic
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
JA
Jais Adapted 7b Chat
Jais · mradermacher
Params7B
Context4K
Q4_K_M4.3 GB
Coding
AV
average-dolphin-8x7B
Average · RichardErkhov
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
ST
StarCoder
StarCoder · mradermacher
Params15.5B
Context8K
Q4_K_M10.0 GB
Coding
LL
CodeLlama 70b Instruct Hf
Llama · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
Coding
GR
Granite 20b Code Base 8k
Granite · mradermacher
Params20B
Context8K
Q4_K_M12.8 GB
Coding

Other quants

Keep browsing