Q2_K_S GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 19715 models have a Q2_K_S file. Sizes run from 2M to 671B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
GR
Granite Speech 3.2 8b
Granite · mradermacher
Params8.17B
Context128K
Q4_K_M4.9 GB
Tool use
ZE
Zerank 1
Zerank · mradermacher
Params4B
Context40K
Q4_K_M2.5 GB
CodingEmbedding
TU
Tucan 27B v1.0
Tucan · mradermacher
Params27.2B
Context8K
Q4_K_M16.6 GB
Tool use
SE
Seed Coder 8B Reasoning
Seed · mradermacher
Params8.25B
Context64K
Q4_K_M5.1 GB
CodingReasoning
MU
G4 31B Musica v1
Musica · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayTool use
RS
RsEvi 8B
Rsevi · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
DE
Qwen3.5 9B DeepSeek 3.2 Intense Auto Variable Thinking
DeepSeek · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningRoleplay
GE
KaLM Embedding Gemma3 12B 2511
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Embedding
LL
Llama 3.1 SuperNova Lite
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
GGUF
MI
Mistralai Mistral Nemo Instruct 2407 Extensive BP Abliteration 12B
Mistral · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
NO
nomic embed code i1
Nomic · mradermacher
Params7.07B
Context32K
Q4_K_M4.4 GB
CodingEmbeddingTool use
QW
Qwen3.5 9B OBLITERATED
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
AY
aya-23-35B
Aya · legraphista
Params35B
Context8K
Smallest8.5 GB
GGUF
QW
Brie v2 Qwen2.5 3b
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
EV
Evilmind 24B v1
Evilmind · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
KI
Kimi Linear 48B A3B Instruct
Kimi · mradermacher
Params49.1B
Context1024K
Q4_K_M29.7 GB
GGUF
QW
FlashModel Qwen3.5 9B
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
MA
Maestro1 9B
Maestro · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
CodingReasoningTool use
IO
IoGPT A1
Iogpt · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Reasoning
WI
Wicked Tutu 31B
Wicked · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
RL
RLinf Math 7B
Rlinf · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
GP
Gpt Oss 20b Stem Distilled Reasoning
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
Reasoning
DA
Dark Pane
Dark · mradermacher
Params11.9B
Context128K
Q4_K_M7.4 GB
GGUF
QW
Qwen3 8B DAG Reasoning
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
DA
Dark Scarlett v1.0 26B A4B
Dark · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
QW
Qwen3 30B A3B Thinking 2507 Claude 4.5 Sonnet High Reasoning Distill
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Reasoning
LL
Llama Primus Merged
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
WI
WinterGoddess 1.4x limarpv3 70B L2 32k Requant
Wintergoddess · NexesQuants
Params69B
Context32K
Smallest14.5 GB
GGUF
QW
Qwen2.5 2X11B CODER Dueling Wolverines 28B
Qwen · mradermacher
Params28B
Context32K
Q4_K_M17.0 GB
Coding
LL
Llama 2 34b Uncode
Llama · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
GGUF

Other quants

Keep browsing