GGUF models by DevQuasar-4

48 GGUF models quantized by DevQuasar-4 on Hugging Face. Sizes run from 494M to 426B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
DE
Huihui ai.DeepSeek R1 Distill Qwen 32B Abliterated
DeepSeek · DevQuasar-4
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
QW
Huihui ai.Qwen2.5 7B Instruct 1M Abliterated
Qwen · DevQuasar-4
Params7.62B
Context986K
Q4_K_M4.7 GB
Tool use
DE
Huihui ai.DeepSeek V3 0324 Pruned Coder 411B
DeepSeek · DevQuasar-4
Params426B
Context160K
Q4_K_M256.6 GB
CodingTool use
GR
Granite 34b Code Instruct 8k
Granite · DevQuasar-4
Params33.7B
Context8K
Q4_K_M21.4 GB
Coding
DA
h2o danube3 500m chat
Danube · DevQuasar-4
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
QW
Qwen2.5 Coder 1.5B
Qwen · DevQuasar-4
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
GL
Glm 4 9b Chat 1m
GLM · DevQuasar-4
Params9.48B
Context1024K
Q4_K_M6.3 GB
Tool use
MI
Codestral 22B v0.1
Mistral · DevQuasar-4
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
MI
mistralai.Mixtral 8x22B v0.1
Mistral · DevQuasar-4
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
QW
Qwen.Qwen2.5 Coder 32B Instruct
Qwen · DevQuasar-4
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingTool use
LL
Llama 3.2 1B Instruct
Llama · DevQuasar-4
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
PO
PowerLM 3b
Powerlm · DevQuasar-4
Params3.51B
Context4K
Q4_K_M2.1 GB
GGUF
QW
Qwen.Qwen2.5 Coder 1.5B
Qwen · DevQuasar-4
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
LL
Meta Llama 3.1 70B Instruct
Llama · DevQuasar-4
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
YU
m a p.YuE s1 7B anneal en cot
Yue · DevQuasar-4
Params6.22B
Context16K
Q4_K_M3.8 GB
GGUF
LL
DevQuasar R1 Uncensored Llama 8B
Llama · DevQuasar-4
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
XL
xLAM 8x7b R
Xlam · DevQuasar-4
Params46.7B
Context32K
Q4_K_M28.4 GB
Tool use
DA
datagemma rig 27b it
Datagemma · DevQuasar-4
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
MI
Mistral Large Instruct 2407
Mistral · DevQuasar-4
Params123B
Context32K
Q4_K_M73.2 GB
GGUF
XL
Salesforce.xLAM 8x22b R
Xlam · DevQuasar-4
Params141B
Context64K
Q4_K_M85.6 GB
Tool use
OL
OLMoE 1B 7B 0924
OLMo · DevQuasar-4
Params6.92B
Context4K
Q4_K_M4.2 GB
GGUF
LL
KingNish.Reasoning Llama 3b v0.1
Llama · DevQuasar-4
Params3.21B
Context128K
Q4_K_M2.0 GB
Reasoning
DA
h2o danube3 4b chat
Danube · DevQuasar-4
Params3.96B
Context8K
Q4_K_M2.4 GB
GGUF
QW
Qwen2.5 Math 72B
Qwen · DevQuasar-4
Params72.7B
Context4K
Q4_K_M47.4 GB
Tool use
AY
CohereForAI.aya Expanse 32b
Aya · DevQuasar-4
Params32.3B
Context8K
Q4_K_M19.8 GB
GGUF
RE
KingNish.Reasoning 0.5b
Reasoning · DevQuasar-4
Params494M
Context32K
Q4_K_M0.4 GB
Reasoning
MI
Mistral NeMo Minitron 8B Instruct
Mistral · DevQuasar-4
Params8.41B
Context8K
Q4_K_M5.1 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · DevQuasar-4
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
mathstral 7B v0.1
Mistral · DevQuasar-4
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
AC
rAIfle.Acolyte 22B
Acolyte · DevQuasar-4
Params22.2B
Context128K
Q4_K_M13.3 GB
Tool use

About DevQuasar-4 on Hugging Face

DevQuasar-4 has published 48 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Mistral. The most downloaded are Huihui ai.DeepSeek R1 Distill Qwen 32B Abliterated, Huihui ai.Qwen2.5 7B Instruct 1M Abliterated and Huihui ai.DeepSeek V3 0324 Pruned Coder 411B.

The quants DevQuasar-4 publishes most often are Q5_K_M (48), Q4_K_M (48), Q3_K_M (48) and Q8_0 (47). Their Q4_K_M files range from 0.3 to 256.6 GB. Parameter counts run from 494M to 426B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has DevQuasar-4 published?

48 models are listed here, mainly from the Llama, Qwen and Mistral families. The most downloaded is Huihui ai.DeepSeek R1 Distill Qwen 32B Abliterated.

Which quants does DevQuasar-4 publish?

The most common are Q5_K_M (48 models), Q4_K_M (48 models), Q3_K_M (48 models) and Q8_0 (47 models).

Keep browsing