GGUF models by DevQuasar-8

86 GGUF models quantized by DevQuasar-8 on Hugging Face. Sizes run from 362M to 671B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
GR
Ibm Granite.Granite 3b Code Base 2k
Granite · DevQuasar-8
Params3.48B
Context2K
Q4_K_M2.1 GB
Coding
QW
Qwen.Qwen2.5 Coder 14B Instruct
Qwen · DevQuasar-8
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
ST
Nexusflow.Starling LM 7B beta
Starling · DevQuasar-8
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
TU
Allenai.Tulu 2 Dpo 7b
Tulu · DevQuasar-8
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
AL
ALLaM AI.ALLaM 7B Instruct Preview
Allam · DevQuasar-8
Params7B
Context4K
Q4_K_M4.3 GB
GGUF
MI
teknium.OpenHermes 2 Mistral 7B
Mistral · DevQuasar-8
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
ST
Bigcode.Starcoder2 15b
StarCoder · DevQuasar-8
Params16B
Context16K
Q4_K_M9.9 GB
Coding
OC
NexaAIDev.octopus planning
Octopus · DevQuasar-8
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
QW
Qwen.Qwen2.5 Coder 3B Instruct
Qwen · DevQuasar-8
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
LL
Llama 2 7b Hf
Llama · DevQuasar-8
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
QW
Qwen.Qwen2.5 Coder 14B
Qwen · DevQuasar-8
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
ZE
Zephyr 7b Beta
Zephyr · DevQuasar-8
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GR
Ibm Granite.Granite 8b Code Instruct 4k
Granite · DevQuasar-8
Params8.05B
Context4K
Q4_K_M4.9 GB
Coding
GR
Ibm Granite.Granite 3.0 3b A800M Base
Granite · DevQuasar-8
Params3.37B
Context4K
Q4_K_M2.1 GB
GGUF
GR
Ibm Granite.Granite 7b Base
Granite · DevQuasar-8
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
OP
open thoughts.OpenThinker 7B
Openthinker · DevQuasar-8
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
LL
Huihui ai.DeepHermes 3 Llama 3 8B Preview Abliterated
Llama · DevQuasar-8
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
SM
davanstrien.Smol Hub tldr
Smol · DevQuasar-8
Params362M
Context8K
Q4_K_M0.3 GB
GGUF
OP
Open thoughts.OpenThinker 32B Unverified
Openthinker · DevQuasar-8
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
QW
Qwen.Qwen2.5 Coder 7B
Qwen · DevQuasar-8
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
LL
Meta llama.Meta Llama 3 8B Instruct
Llama · DevQuasar-8
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GR
Ibm Granite.Granite 3.0 8b Instruct
Granite · DevQuasar-8
Params8.17B
Context4K
Q4_K_M4.9 GB
Tool use
MI
mistralai.Mistral 7B Instruct v0.1
Mistral · DevQuasar-8
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GO
goppa ai.Goppa LogiLlama
Goppa · DevQuasar-8
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
QW
Qwen.CodeQwen1.5 7B
Qwen · DevQuasar-8
Params7.25B
Context64K
Q4_K_M4.7 GB
GGUF
QW
Qwen.Qwen2 1.5B Instruct
Qwen · DevQuasar-8
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
Qwen.Qwen2.5 Math 7B
Qwen · DevQuasar-8
Params7.62B
Context4K
Q4_K_M4.7 GB
Tool use
MI
Mistral Small 24B Instruct 2501
Mistral · DevQuasar-8
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
LL
DavidAU.DeepThought MOE 8X3B R1 Llama 3.2 Reasoning 18B
Llama · DevQuasar-8
Params18.4B
Context128K
Q4_K_M11.3 GB
Reasoning
GR
Ibm Granite.Granite 3.0 2b Base
Granite · DevQuasar-8
Params2.53B
Context4K
Q4_K_M1.5 GB
GGUF

About DevQuasar-8 on Hugging Face

DevQuasar-8 has published 86 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Granite. The most downloaded are Ibm Granite.Granite 3b Code Base 2k, Qwen.Qwen2.5 Coder 14B Instruct and Nexusflow.Starling LM 7B beta.

The quants DevQuasar-8 publishes most often are Q2_K (86), Q8_0 (85), Q6_K (85) and Q5_K_M (85). Their Q4_K_M files range from 0.3 to 42.5 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-8 published?

86 models are listed here, mainly from the Qwen, Llama and Granite families. The most downloaded is Ibm Granite.Granite 3b Code Base 2k.

Which quants does DevQuasar-8 publish?

The most common are Q2_K (86 models), Q8_0 (85 models), Q6_K (85 models) and Q5_K_M (85 models).

Keep browsing