GGUF models by DevQuasar-7

104 GGUF models quantized by DevQuasar-7 on Hugging Face. Sizes run from 362M to 406B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Dolphin 3.0 Llama 3.1 8B
Llama · DevQuasar-7
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
DE
Huihui ai.DeepSeek R1 Distill Qwen 7B Abliterated
DeepSeek · DevQuasar-7
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
DE
Huihui ai.DeepSeek R1 Distill Qwen 14B Abliterated v2
DeepSeek · DevQuasar-7
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
LL
LLM4Binary.llm4decompile 6.7b v1.5
Llm · DevQuasar-7
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
QW
qingy2024.Qwen2.5 4B
Qwen · DevQuasar-7
Params4.17B
Context32K
Q4_K_M2.6 GB
Tool use
QW
Huihui ai.Qwen2.5 14B Instruct 1M Abliterated
Qwen · DevQuasar-7
Params14.8B
Context986K
Q4_K_M9.0 GB
Tool use
LL
LLM4Binary.llm4decompile 6.7b v2
Llm · DevQuasar-7
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
ST
Fortytwo Network.Strand Rust Coder 14B v1
Strand · DevQuasar-7
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
DE
Deepseek ai.DeepSeek R1 Distill Qwen 7B
DeepSeek · DevQuasar-7
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
SM
prithivMLmods.SmolLM2 360M Grpo r999
SmolLM · DevQuasar-7
Params362M
Context8K
Q4_K_M0.3 GB
GGUF
MI
Minitron 8B Base
Minitron · DevQuasar-7
Params8.27B
Context4K
Q4_K_M5.2 GB
GGUF
DE
Deepseek ai.DeepSeek R1 Distill Qwen 1.5B
DeepSeek · DevQuasar-7
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
GR
Ibm Granite.Granite 3b Code Instruct 2k
Granite · DevQuasar-7
Params3.48B
Context2K
Q4_K_M2.1 GB
Coding
GR
Ibm Granite.Granite 3.0 8b Base
Granite · DevQuasar-7
Params8.17B
Context4K
Q4_K_M4.9 GB
GGUF
GR
Ibm Granite.Granite 8b Code Instruct 128k
Granite · DevQuasar-7
Params8.05B
Context125K
Q4_K_M4.9 GB
Coding
OP
allenai.open instruct code alpaca 7b
Open · DevQuasar-7
Params6.74B
Context2K
Q4_K_M4.1 GB
Coding
AC
nvidia.AceMath 1.5B Instruct
Acemath · DevQuasar-7
Params1.78B
Context4K
Q4_K_M1.1 GB
GGUF
LL
allenai.Llama 3.1 Tulu 3 8B
Llama · DevQuasar-7
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
OP
Huihui ai.OpenThinker 7B Abliterated
Openthinker · DevQuasar-7
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
LL
Dolphin 3.0 Llama 3.2 1b
Llama · DevQuasar-7
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
LL
Dolphin 3.0 Llama 3.2 3B
Llama · DevQuasar-7
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
OP
prithivMLmods.Open R1 Mini Experimental
Open · DevQuasar-7
Params1.54B
Context32K
Q4_K_M1.0 GB
Reasoning
MI
mistralai.Mistral Small 24B Instruct 2501
Mistral · DevQuasar-7
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
DE
Deepseek ai.DeepSeek R1 Distill Qwen 14B
DeepSeek · DevQuasar-7
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
LL
ilsp.Llama Krikri 8B Base
Llama · DevQuasar-7
Params8.2B
Context128K
Q4_K_M5.0 GB
Tool use
IN
Internlm.Internlm2_5 7b Chat
InternLM · DevQuasar-7
Params7.74B
Context32K
Q4_K_M4.7 GB
GGUF
MI
Dolphin3.0 Mistral 24B
Mistral · DevQuasar-7
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
AC
nvidia.AceMath 7B Instruct
Acemath · DevQuasar-7
Params7.62B
Context4K
Q4_K_M4.7 GB
GGUF
HU
Huihui Ai.S1.1 32B Abliterated
Huihui · DevQuasar-7
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
IN
internlm.OREAL 32B SFT
InternLM · DevQuasar-7
Params32.8B
Context128K
Q4_K_M19.9 GB
Tool use

About DevQuasar-7 on Hugging Face

DevQuasar-7 has published 104 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and DeepSeek. The most downloaded are Dolphin 3.0 Llama 3.1 8B, Huihui ai.DeepSeek R1 Distill Qwen 7B Abliterated and Huihui ai.DeepSeek R1 Distill Qwen 14B Abliterated v2.

The quants DevQuasar-7 publishes most often are Q6_K (104), Q5_K_M (104), Q4_K_M (104) and Q3_K_M (104). Their Q4_K_M files range from 0.3 to 243.1 GB. Parameter counts run from 362M to 406B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has DevQuasar-7 published?

104 models are listed here, mainly from the Llama, Qwen and DeepSeek families. The most downloaded is Dolphin 3.0 Llama 3.1 8B.

Which quants does DevQuasar-7 publish?

The most common are Q6_K (104 models), Q5_K_M (104 models), Q4_K_M (104 models) and Q3_K_M (104 models).

Keep browsing