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
GE
Gemma 3 27b It Abliterated
Gemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
ME
MedicalQwen3 Reasoning 14B IT
Medicalqwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
QW
Qwen2.5 Coder 7B Instruct Heretic
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
DE
Qwen3 30B A3B Thinking 2507 Deepseek v3.1 Distill V2 FP32
DeepSeek · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingReasoning
NO
NovaAI
Novaai · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GE
claude 3.7 sonnet reasoning gemma3 12B i1
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Reasoning
DU
DuckDB-NSQL-7B-v0.1
Duckdb · duyntnet
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF
LF
LFM2.5 8B A1B Coder
Lfm · mradermacher
Params8.47B
Context125K
Q4_K_M5.2 GB
CodingReasoningTool use
TR
Triumvirate Qwopus MiMo Ornith 9B Coder
Triumvirate · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoning
MI
Mistral Small 4 119B 2603
Mistral · mradermacher
Params119B
Context1024K
Q4_K_M72.2 GB
GGUF
QW
Qwen2.5 VL 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
GR
granite 3.1 8b Reasoning i1
Granite · mradermacher
Params8.17B
Context128K
Q4_K_M4.9 GB
Reasoning
GE
Copywriter Gemma4 31b
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
EU
L3.3 70B Euryale v2.3 i1
Euryale · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
AU
MS3.2 Austral Winton
Austral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
LL
Meta Llama 3.1 8B Instruct Abliterated
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
GGUF
CH
Chunky-Lemon-Cookie-11B
Chunky · backyardai
Params10.7B
Context32K
Q4_K_M6.5 GB
Roleplay
DE
DeepHat V1 7B Heretic Abliterated
Deephat · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Qwen3 54B A3B 2507 YOYO2 TOTAL RECALL Instruct
Qwen · mradermacher
Params53B
Context986K
Q4_K_M32.1 GB
CodingReasoningTool use
LL
Turkish Llama 8b v0.1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
TI
Tinyllama 1.1b Abliterated
Tinyllama · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
QW
MARTHA LXVIII.21b_QWEN 3.5 3.6_prune_27b 3.6_base
Qwen · mradermacher
Params20.8B
Context256K
Q4_K_M12.9 GB
RoleplayVision
QW
Qwen3 Coder Next REAM
Qwen · mradermacher
Params60B
Context256K
Q4_K_M36.7 GB
Coding
QW
Qwen3.5 122B A10B Claude Distill
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
Vision
GE
Gemma 4 12b Heretic Abliterated
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
GE
Gemma 3 27b It Heretic
Gemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
Coding
IN
INF AZ 7B 0524
Inf · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
CH
Chimpgpt Coder Elite
Chimpgpt · mradermacher
Params29.9B
Context198K
Q4_K_M18.1 GB
CodingReasoningTool use
AS
AstraGPTCoder 7B i1
Astragptcoder · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingReasoning
OL
Olmo 3 7B Think DPO
OLMo · mradermacher
Params7.3B
Context64K
Q4_K_M4.5 GB
Reasoning

Other quants

Keep browsing