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
WI
Wicked Tutu 31B v4
Wicked · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayTool use
TA
UI TARS 7B DPO
Tars · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
JA
Jais Family 13b Chat
Jais · mradermacher
Params13.5B
Context2K
Q4_K_M9.0 GB
Coding
MU
Muse Glimmer 30B Hermes Agentic
Muse · mradermacher
Params27.9B
Context128K
Q4_K_M16.9 GB
ReasoningTool use
LL
LLaDA 1.5
Llada · mradermacher
Params8.02B
Context4K
Q4_K_M4.9 GB
GGUF
GE
Gemma 4 26B A4B It Abliterix
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
GE
Gemma 2 Mitra E
Gemma · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
Embedding
QW
Qwen2.5 14B Instruct 1M Abliterated
Qwen · mradermacher
Params14.8B
Context986K
Q4_K_M9.0 GB
Tool use
MI
Mistral 2x24B MOE Magistral 2506 Devstral 2507 1.1 Coder Reasoning Ultimate 44B
Mistral · mradermacher
Params43.7B
Context128K
Q4_K_M26.5 GB
CodingReasoning
TE
Tensor 10B Coder
Tensor · mradermacher
Params9.95B
Context195K
Q4_K_M6.1 GB
CodingTool use
PA
MS3.2 PaintedFantasy v4.1 24B Heretic v1
Paintedfantasy · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingRoleplay
QW
Suri Qwen 3.5 9B Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
FR
Friday 35B
Friday · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
CodingReasoningTool use
OP
OpenLumen 2 Pulsar
Openlumen · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
ST
Starstreak 7b alpha i1
Starstreak · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
Savage Sands 12B
Savage · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
HE
G Health 14B Instruct
Health · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
LF
LFM2.5 Encoder 350M Diffusion
Lfm · mradermacher
Params354M
Context125K
Q4_K_M0.2 GB
Coding
HY
HyGPT 10b
Hygpt · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Qwen36 35B Opus Reasoning Merged
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Reasoning
MI
Mistral Darwin 7b v0.1 i1
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
PA
MS3.2 PaintedFantasy v2 24B
Paintedfantasy · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
MM
MMR1 Math v0 7B
Mmr · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Tool use
PR
Prism Coder 14b
Prism · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Coding
DA
G2 Darkest Writer Dirty Shirley 9B v2
Darkest · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
MamayLM Gemma 3 12B IT v1.0
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Reasoning
SI
Silicon-Maid-7B
Silicon · duyntnet
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
CR
Crimson Twilight 12B
Crimson · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
LL
Llama 3 8B dutch i1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.3 8B Instruct Thinking Claude Haiku 4.5 High Reasoning 1700x
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplayTool use

Other quants

Keep browsing