GGUF models by DevQuasar-3

61 GGUF models quantized by DevQuasar-3 on Hugging Face. Sizes run from 14M to 1000B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3.2 1B
Llama · DevQuasar-3
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
QW
Qwen2.5 Coder 7B Instruct
Qwen · DevQuasar-3
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
DE
Deepseek ai.DeepSeek R1 Distill Llama 8B
DeepSeek · DevQuasar-3
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
LL
amd.AMD Llama 135m code
Llama · DevQuasar-3
Params134M
Context2K
Q4_K_M0.1 GB
Coding
OL
OLMoE 1B 7B 0924 Instruct
OLMo · DevQuasar-3
Params6.92B
Context4K
Q4_K_M4.2 GB
GGUF
XL
xLAM 1b Fc R
Xlam · DevQuasar-3
Params1.35B
Context16K
Q4_K_M0.9 GB
Tool use
RI
inclusionAI.Ring 1T
Ring · DevQuasar-3
Params1000B
Context64K
Q4_K_M604.2 GB
ReasoningTool use
GE
INSAIT Institute.BgGPT Gemma 2 2.6B IT v1.0
Gemma · DevQuasar-3
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
RE
reader lm 1.5b
Reader · DevQuasar-3
Params1.54B
Context250K
Q4_K_M1.0 GB
GGUF
NU
NuExtract Tiny v1.5
Nuextract · DevQuasar-3
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
ST
Stable Code Instruct 3b
Stable · DevQuasar-3
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
TI
KBlueLeaf.TIPO 500M
Tipo · DevQuasar-3
Params508M
Context2K
Q4_K_M0.3 GB
GGUF
AY
CohereForAI.aya Expanse 8b
Aya · DevQuasar-3
Params8.03B
Context8K
Q4_K_M5.1 GB
GGUF
DE
Deepseek ai.DeepSeek V3 Base Bf16
DeepSeek · DevQuasar-3
Params671B
Context160K
Smallest244.0 GB
Tool use
SH
Shieldgemma 9b
Shieldgemma · DevQuasar-3
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
IN
OpenSafetyLab.MD Judge V0_2 Internlm2_7B
InternLM · DevQuasar-3
Params7.74B
Context32K
Q4_K_M4.7 GB
GGUF
GR
Ibm Granite.Granite 3.0 1b A400M Instruct
Granite · DevQuasar-3
Params1.33B
Context4K
Q4_K_M0.8 GB
Tool use
SH
shuttleai.shuttle 3
Shuttle · DevQuasar-3
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
LL
Llama3.1 70B ShiningValiant2
Llama · DevQuasar-3
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
Llama 3.1 Tulu 3 8B SFT
Llama · DevQuasar-3
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
AR
katanemo.Arch Function 3B
Arch · DevQuasar-3
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
FL
flowaicom.Flow Judge v0.1
Flow · DevQuasar-3
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
PH
grounded ai.phi3.5 rag relevance judge merge
Phi · DevQuasar-3
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
LL
Llama 3 8B ProLong 512k Instruct
Llama · DevQuasar-3
Params8.03B
Context512K
Q4_K_M4.9 GB
GGUF
EX
LGAI EXAONE.EXAONE 3.0 7.8B Instruct
Exaone · DevQuasar-3
Params7.82B
Context4K
Q4_K_M4.8 GB
GGUF
GE
Google.Gemma 2b Aps It
Gemma · DevQuasar-3
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
QW
Openbuddy Qwen2.5Llamaify 14b v23.1 200k
Qwen · DevQuasar-3
Params14.8B
Context195K
Q4_K_M9.0 GB
GGUF
MI
TencentARC.MetaMath Mistral Pro
Mistral · DevQuasar-3
Params8.99B
Context32K
Q4_K_M5.4 GB
GGUF
MI
mistralai.Ministral 8B Instruct 2410
Mistral · DevQuasar-3
Params8.02B
Context32K
Q4_K_M4.9 GB
Tool use
DE
Qwen2.5 32B
DeepSeek · DevQuasar-3
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use

About DevQuasar-3 on Hugging Face

DevQuasar-3 has published 61 GGUF models that ggufmodels.com tracks, across families such as Llama, Mistral and DeepSeek. The most downloaded are Llama 3.2 1B, Qwen2.5 Coder 7B Instruct and Deepseek ai.DeepSeek R1 Distill Llama 8B.

The quants DevQuasar-3 publishes most often are Q3_K_M (60), Q2_K (60), Q8_0 (58) and Q5_K_M (58). Their Q4_K_M files range from 0.0 to 604.2 GB. Parameter counts run from 14M to 1000B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has DevQuasar-3 published?

61 models are listed here, mainly from the Llama, Mistral and DeepSeek families. The most downloaded is Llama 3.2 1B.

Which quants does DevQuasar-3 publish?

The most common are Q3_K_M (60 models), Q2_K (60 models), Q8_0 (58 models) and Q5_K_M (58 models).

Keep browsing