GGUF models by DevQuasar

833 GGUF models quantized by DevQuasar on Hugging Face. Sizes run from 82M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Huihui ai.Qwen2.5 0.5B Instruct Abliterated v3
Qwen · DevQuasar
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
HO
Hcompany.Holotron4 30B A3B
Holotron · DevQuasar
Params31.6B
Context1024K
Smallest17.9 GB
ReasoningTool useVision
NE
nvidia.Nemotron 3 Nano Omni 30B A3B Reasoning BF16
Nemotron · DevQuasar
Params31.6B
Context1024K
Smallest17.9 GB
ReasoningTool useVision
DR
Dream org.Dream Coder v0 Instruct 7B
Dream · DevQuasar
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
MA
Salesforce.E1 Math 7B
Math · DevQuasar
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
NA
Nanbeige.Nanbeige4.1 3B
Nanbeige · DevQuasar
Params3.93B
Context256K
Q4_K_M2.4 GB
ReasoningTool use
QW
Qwen.Qwen3 1.7B
Qwen · DevQuasar
Params2.03B
Context40K
Q4_K_M1.3 GB
ReasoningTool use
KA
Kwaipilot.KAT V1 40B
Kat · DevQuasar
Params40.6B
Context128K
Q4_K_M24.6 GB
Tool use
QW
Qwen.Qwen3 VL 30B A3B Instruct
Qwen · DevQuasar
Params30.5B
Context256K
Q4_K_M18.6 GB
Tool useVision
RU
inclusionAI.Rubicon Preview
Rubicon · DevQuasar
Params30.5B
Context40K
Q4_K_M18.6 GB
ReasoningTool use
DA
Alibaba Apsara.DASD 30B A3B Thinking Preview
Dasd · DevQuasar
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool use
FO
Fdtn ai.Foundation Sec 8B Reasoning
Foundation · DevQuasar
Params8.03B
Context128K
Q4_K_M4.9 GB
Reasoning
NA
nanonets.Nanonets OCR2 3B
Nanonets · DevQuasar
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
QW
Aratako.Qwen3 8B NSFW JP
Qwen · DevQuasar
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
FL
fluently.FluentlyQwen3 Coder 4B 0909
Fluentlyqwen · DevQuasar
Params4.02B
Context40K
Q4_K_M2.5 GB
CodingReasoningTool use
GR
Qiskit.granite 3.3 8b Qiskit
Granite · DevQuasar
Params8.17B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
BF
ByteDance Seed.BFS Prover V1 7B
Bfs · DevQuasar
Params7.62B
Context4K
Q4_K_M4.7 GB
Tool use
QW
Huihui ai.Huihui Qwen3 4B Instruct 2507 Abliterated
Qwen · DevQuasar
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
GL
Arcee ai.GLM 4 32B Base 32K
GLM · DevQuasar
Params32.6B
Context32K
Q4_K_M19.7 GB
GGUF
QW
Qwen.Qwen3 VL 8B Thinking
Qwen · DevQuasar
Params8.19B
Context256K
Q4_K_M5.0 GB
ReasoningTool useVision
SE
Intelligent Internet.II Search 4B
Search · DevQuasar
Params4.41B
Context96K
Q4_K_M2.7 GB
ReasoningTool use
FA
Falcon
Falcon · DevQuasar
Params11.1B
Context2K
Q4_K_M6.8 GB
GGUF
PA
zerofata.MS3.2 PaintedFantasy Visage v2 33B
Paintedfantasy · DevQuasar
Params33.6B
Context128K
Q4_K_M20.4 GB
GGUF
GP
P E W.Gpt Oss 20b Heretic
gpt-oss · DevQuasar
Params20.9B
Context128K
Q4_K_M15.8 GB
Tool use
NE
nvidia.Nemotron Cascade 8B
Nemotron · DevQuasar
Params8.19B
Context32K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen.Qwen3.5 4B
Qwen · DevQuasar
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
VI
WeiboAI.VibeThinker 1.5B
Vibethinker · DevQuasar
Params1.78B
Context128K
Q4_K_M1.1 GB
Tool use
SM
PowerInfer.SmallThinker 4BA0.6B Instruct
Smallthinker · DevQuasar
Params4.27B
Context32K
Q4_K_M2.6 GB
Tool use
QW
Qwen.Qwen3 VL 8B Instruct
Qwen · DevQuasar
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
NE
nvidia.Nemotron Cascade 2 30B A3B
Nemotron · DevQuasar
Params31.6B
Context1024K
Q4_K_M24.5 GB
ReasoningTool use

Keep browsing