GGUF models by DevQuasar-11

35 GGUF models quantized by DevQuasar-11 on Hugging Face. Sizes run from 362M to 671B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
OP
All Hands.Openhands Lm 1.5b v0.1
Openhands · DevQuasar-11
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
RI
inclusionAI.Ring Flash 2.0
Ring · DevQuasar-11
Params103B
Context32K
Q4_K_M62.4 GB
GGUF
MY
Mythomax L2 13b
Mythomax · DevQuasar-11
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
MX
Mxbai Rerank Large v2
Mxbai · DevQuasar-11
Params1.54B
Context32K
Q4_K_M1.0 GB
EmbeddingTool use
GR
Ibm Granite.Granite Guardian 3.1 2b
Granite · DevQuasar-11
Params2.53B
Context128K
Q4_K_M1.5 GB
Tool use
GR
Ibm Granite.Granite Guardian 3.2 3b A800M
Granite · DevQuasar-11
Params3.3B
Context128K
Q4_K_M2.0 GB
Tool use
PA
Pantheon Rp Pure 1.6.2 22b Small
Pantheon · DevQuasar-11
Params22.2B
Context128K
Q4_K_M13.3 GB
RoleplayTool use
MX
Mxbai Rerank Base v2
Mxbai · DevQuasar-11
Params494M
Context32K
Q4_K_M0.4 GB
EmbeddingTool use
CO
Deepcogito.Cogito 671b v2.1
Cogito · DevQuasar-11
Params671B
Context160K
Q4_K_M404.5 GB
ReasoningTool use
TX
Google.Txgemma 2b Predict
Txgemma · DevQuasar-11
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
MI
Mistral Small 3.1 DRAFT 0.5B
Mistral · DevQuasar-11
Params593M
Context32K
Q4_K_M0.5 GB
GGUF
GE
YFolla.gemma 3 Dnd
Gemma · DevQuasar-11
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
ML
mlfoundations dev.glaive reasoning 300k
Mlfoundations · DevQuasar-11
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use
LL
Meta llama.Meta Llama 3 70B Instruct
Llama · DevQuasar-11
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
EX
LGAI EXAONE.EXAONE Deep 7.8B
Exaone · DevQuasar-11
Params7.82B
Context32K
Q4_K_M4.8 GB
GGUF
ML
mlfoundations dev.openthoughts plus ioi cots
Mlfoundations · DevQuasar-11
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
TR
trillionlabs.Trillion 7B Preview
Trillion · DevQuasar-11
Params7.53B
Context4K
Q4_K_M4.6 GB
GGUF
SM
HuggingFaceTB.SmolLM2 360M Instruct
SmolLM · DevQuasar-11
Params362M
Context8K
Q4_K_M0.3 GB
GGUF
PA
Pantheon Rp 1.6 12b Nemo Kto
Pantheon · DevQuasar-11
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
DA
Steelskull.L3.3 Damascus R1
Damascus · DevQuasar-11
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
TX
Google.Txgemma 9b Chat
Txgemma · DevQuasar-11
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
TX
Google.Txgemma 9b Predict
Txgemma · DevQuasar-11
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
NE
Steelskull.L3.3 MS Nevoria 70b
Nevoria · DevQuasar-11
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LI
qihoo360.Light R1 7B DS
Light · DevQuasar-11
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
LL
Rinna.Llama 3 Youko 70b Instruct
Llama · DevQuasar-11
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
NE
Steelskull.L3.3 Nevoria R1 70b
Nevoria · DevQuasar-11
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
PA
Pantheon Rp 1.5 12b Nemo
Pantheon · DevQuasar-11
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
SO
upstage.Solar Open 100B
Solar · DevQuasar-11
Params103B
Context128K
Q4_K_M62.3 GB
Tool use
ML
mlfoundations dev.glaive reasoning 100k
Mlfoundations · DevQuasar-11
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use
ML
mlfoundations dev.openthoughts plus glaive reasoning 100k
Mlfoundations · DevQuasar-11
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use

About DevQuasar-11 on Hugging Face

DevQuasar-11 has published 35 GGUF models that ggufmodels.com tracks, across families such as Pantheon, Mlfoundations and Llama. The most downloaded are All Hands.Openhands Lm 1.5b v0.1, inclusionAI.Ring Flash 2.0 and Mythomax L2 13b.

The quants DevQuasar-11 publishes most often are Q8_0 (35), Q5_K_M (35), Q4_K_M (35) and Q3_K_M (35). Their Q4_K_M files range from 0.3 to 404.5 GB. Parameter counts run from 362M to 671B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has DevQuasar-11 published?

35 models are listed here, mainly from the Pantheon, Mlfoundations and Llama families. The most downloaded is All Hands.Openhands Lm 1.5b v0.1.

Which quants does DevQuasar-11 publish?

The most common are Q8_0 (35 models), Q5_K_M (35 models), Q4_K_M (35 models) and Q3_K_M (35 models).

Keep browsing