GGUF models by DevQuasar-2

37 GGUF models quantized by DevQuasar-2 on Hugging Face. Sizes run from 135M to 123B parameters. The longest trained context is 986K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen.Qwen2 VL 7B Instruct
Qwen · DevQuasar-2
Params676M
Context32K
Q4_K_M4.7 GB
Vision
GR
Granite 8b Code Base 128k
Granite · DevQuasar-2
Params8.05B
Context125K
Q4_K_M4.9 GB
Coding
GR
Granite 20b Code Instruct 8k
Granite · DevQuasar-2
Params20.1B
Context8K
Q4_K_M12.8 GB
Coding
PH
microsoft.phi 4
Phi · DevQuasar-2
Params14.7B
Context16K
Q4_K_M9.1 GB
GGUF
OL
OLMo 7B 0724 Instruct Hf
OLMo · DevQuasar-2
Params6.89B
Context4K
Q4_K_M4.2 GB
GGUF
RA
prithivMLmods.Raptor X5 UIGEN
Raptor · DevQuasar-2
Params14.8B
Context117K
Q4_K_M9.0 GB
Tool use
DI
Dinobot Opus 14B Exp
Dinobot · DevQuasar-2
Params14.8B
Context128K
Q4_K_M9.0 GB
Tool use
LL
Meta llama.Llama 3.3 70B Instruct
Llama · DevQuasar-2
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
TR
prithivMLmods.Triangulum 10B
Triangulum · DevQuasar-2
Params10.3B
Context32K
Q4_K_M6.3 GB
GGUF
SQ
Sqweeks 7B Instruct
Sqweeks · DevQuasar-2
Params7.62B
Context8K
Q4_K_M4.7 GB
Tool use
QW
prithivMLmods.QwQ MathOct 7B
Qwen · DevQuasar-2
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use
GW
prithivMLmods.GWQ 9B Preview
Gwq · DevQuasar-2
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
SM
prithivMLmods.SmolLM2 135M Grpo Gsm8k
SmolLM · DevQuasar-2
Params135M
Context8K
Q4_K_M0.1 GB
GGUF
CY
TheDrummer.Cydonia 24B v4.1
Cydonia · DevQuasar-2
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
QW
prithivMLmods.GN 108036 Qwen 14B
Qwen · DevQuasar-2
Params14.8B
Context986K
Q4_K_M9.0 GB
Tool use
CO
prithivMLmods.Condor Opus 14B Exp
Condor · DevQuasar-2
Params14.8B
Context986K
Q4_K_M9.0 GB
GGUF
ME
prithivMLmods.Megatron Opus 14B 2.0
Megatron · DevQuasar-2
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
PH
prithivMLmods.Phi 4 Empathetic
Phi · DevQuasar-2
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
QW
prithivMLmods.Phi 4 QwQ
Qwen · DevQuasar-2
Params14.7B
Context16K
Q4_K_M8.9 GB
Reasoning
QW
prithivMLmods.Gamma Corvi Qwen 14B
Qwen · DevQuasar-2
Params14.8B
Context986K
Q4_K_M9.0 GB
Tool use
EV
Evac Opus 14B Exp
Evac · DevQuasar-2
Params14.8B
Context128K
Q4_K_M9.0 GB
Tool use
CA
prithivMLmods.Caption Pro
Caption · DevQuasar-2
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
ME
prithivMLmods.Mensa Beta 14B Instruct
Mensa · DevQuasar-2
Params14.8B
Context128K
Q4_K_M9.0 GB
Tool use
RA
prithivMLmods.Raptor X2
Raptor · DevQuasar-2
Params14.8B
Context117K
Q4_K_M9.0 GB
Tool use
VI
prithivMLmods.Viper Coder Hybrid v1.3
Viper · DevQuasar-2
Params14.8B
Context128K
Q4_K_M9.0 GB
CodingTool use
RA
prithivMLmods.Raptor X4
Raptor · DevQuasar-2
Params14.8B
Context117K
Q4_K_M9.0 GB
Tool use
QW
prithivMLmods.QWQ 500M
Qwen · DevQuasar-2
Params494M
Context32K
Q4_K_M0.4 GB
ReasoningTool use
CY
TheDrummer.Cydonia 24B v2
Cydonia · DevQuasar-2
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
GW
prithivMLmods.GWQ2b
Gwq · DevQuasar-2
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
RA
prithivMLmods.Raptor X3
Raptor · DevQuasar-2
Params14.8B
Context117K
Q4_K_M9.0 GB
Tool use

About DevQuasar-2 on Hugging Face

DevQuasar-2 has published 37 GGUF models that ggufmodels.com tracks, across families such as Qwen, Raptor and Phi. The most downloaded are Qwen.Qwen2 VL 7B Instruct, Granite 8b Code Base 128k and Granite 20b Code Instruct 8k.

The quants DevQuasar-2 publishes most often are Q5_K_M (36), Q4_K_M (36), Q3_K_M (36) and Q2_K (36). Their Q4_K_M files range from 0.1 to 73.2 GB. Parameter counts run from 135M to 123B, and the longest trained context window is 986K tokens.

Frequently asked questions

What GGUF models has DevQuasar-2 published?

37 models are listed here, mainly from the Qwen, Raptor and Phi families. The most downloaded is Qwen.Qwen2 VL 7B Instruct.

Which quants does DevQuasar-2 publish?

The most common are Q5_K_M (36 models), Q4_K_M (36 models), Q3_K_M (36 models) and Q2_K (36 models).

Keep browsing