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
QW
Qwen3 ST The Next Generation II v1 256k Ctx 6B
Qwen · mradermacher
Params6.33B
Context256K
Q4_K_M3.9 GB
CodingReasoningTool use
BI
BiMediX2 8B Hf
Bimedix · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
HE
HERETICODER 2.5 7B IT
Hereticoder · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
LL
Llama 3 JPRP NSFW 8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
ReasoningRoleplay
GE
Gemma 3 1B It GLM 4.7 Flash Heretic Uncensored Thinking
Gemma · mradermacher
Params1B
Context32K
Q4_K_M0.8 GB
Reasoning
PH
Phi 3 medium 128k instruct imatrix
Phi · hermes42
Params14B
Context128K
Q4_K_M8.6 GB
CodingTool use
QW
GeoLLM Qwen3.5 27B
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
QW
Qwen2.5 32B Instruct Darija
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
QW
OneThinker SFT Qwen3 8B
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool use
AZ
Aztec Coder 4B
Aztec · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoningTool use
CA
CantoneseLLM v2.0 30B A3B Thinking
Cantonesellm · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
Reasoning
YI
Yi-6B-Chat
Yi · mradermacher
Params6.06B
Context4K
Q4_K_M3.7 GB
GGUF
QW
shisa v2.1 qwen3 8b i1
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
LL
Llama3.2 3B Math Gsm8K AutoSFT
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
GE
Gemma 4 AssGuard 31B
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
OL
OLMoE 1B 7B 0125 i1
OLMo · mradermacher
Params6.9B
Context4K
Q4_K_M4.2 GB
GGUF
UW
UwU 14B Math v0.2 i1
Uwu · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
OM
Omni R1 Zero
Omni · mradermacher
Params7.01B
Context10K
Q4_K_M4.3 GB
Reasoning
MI
Huihui Ministral 3 3B Reasoning 2512 Abliterated
Mistral · mradermacher
Params3.43B
Context256K
Q4_K_M2.1 GB
Reasoning
LL
Arabic llama3 i1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
GR
Granite Guardian 3.3 8b
Granite · mradermacher
Params8.17B
Context128K
Q4_K_M4.9 GB
GGUF
GE
Gemma 4 26B A4B It Heretic Antislop
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
QW
Qwopus3.5 9B v3
Qwopus · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Reasoning
FA
gpt4all falcon i1
Falcon · mradermacher
Params7.22B
Context2K
Q4_K_M5.0 GB
GGUF
ZH
Zhi Create DSR1 14B
Zhi · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
SH
Shisa K 12B
Shisa · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
QI
QiMing Janus
Qiming · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
SW
SWE Review 8B
Swe · mradermacher
Params8.19B
Context160K
Q4_K_M5.0 GB
Coding
MA
Magidonia 24B v4.3 Heretic v4
Magidonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Tool use
DE
Delexa-Instruct-V0.1-7b
Delexa · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

Other quants

Keep browsing