DevQuasar

community

Verified

https://devquasar.com/

Activity Feed

AI & ML interests

Open-Source LLMs, Local AI Projects: https://pypi.org/project/llm-predictive-router/

Recent Activity

csabakecskemeti updated a model about 2 hours ago

DevQuasar/moonshotai.Kimi-Dev-72B-GGUF

csabakecskemeti new activity 1 day ago

DevQuasar/NousResearch.DeepHermes-3-Llama-3-8B-Preview-GGUF:## 🚨Missing License: May Violate LLaMA 3 Community License

csabakecskemeti updated a model 1 day ago

DevQuasar/NousResearch.DeepHermes-3-Llama-3-8B-Preview-GGUF

View all activity

DevQuasar's activity

csabakecskemeti

updated a model about 2 hours ago

DevQuasar/moonshotai.Kimi-Dev-72B-GGUF

Text Generation • Updated about 2 hours ago • 28

csabakecskemeti

in DevQuasar/NousResearch.DeepHermes-3-Llama-3-8B-Preview-GGUF 1 day ago

## 🚨Missing License: May Violate LLaMA 3 Community License

👍 1

#1 opened 1 day ago by

xixi126

csabakecskemeti

updated 2 models 1 day ago

DevQuasar/NousResearch.DeepHermes-3-Llama-3-8B-Preview-GGUF

Text Generation • Updated 1 day ago • 166 • 3

DevQuasar/Tesslate.UIGEN-T3-32B-Preview-GGUF

Text Generation • Updated 1 day ago • 78

csabakecskemeti

in DevQuasar/Tesslate.UIGEN-T3-32B-Preview-GGUF 1 day ago

Concern About Standard Quants

#1 opened 2 days ago by

davidpfarrell

csabakecskemeti

published a model 2 days ago

DevQuasar/moonshotai.Kimi-Dev-72B-GGUF

Text Generation • Updated about 2 hours ago • 28

csabakecskemeti

updated a model 2 days ago

DevQuasar/nvidia.AceReason-Nemotron-1.1-7B-GGUF

Text Generation • Updated 2 days ago • 56

csabakecskemeti

published a model 2 days ago

DevQuasar/nvidia.AceReason-Nemotron-1.1-7B-GGUF

Text Generation • Updated 2 days ago • 56

csabakecskemeti

updated a model 2 days ago

DevQuasar/huihui-ai.Qwen3-16B-A3B-abliterated-GGUF

Text Generation • Updated 2 days ago • 162

csabakecskemeti

published a model 2 days ago

DevQuasar/huihui-ai.Qwen3-16B-A3B-abliterated-GGUF

Text Generation • Updated 2 days ago • 162

csabakecskemeti

updated a model 2 days ago

DevQuasar/dmis-lab.llama-3.1-medprm-reward-v1.0-GGUF

Text Generation • Updated 2 days ago • 68

csabakecskemeti

posted an update 9 days ago

Post

2739

Has anyone ever backed up a model to a sequential tape drive, or I'm the world first? :D
Just played around with my retro PC that has got a tape drive—did it just because I can.

5 replies

csabakecskemeti

posted an update 22 days ago

Post

326

Deepseek R1 0528 Q2 locally.
(I believe it has overthinking it a bit :) )
https://youtu.be/Iqu5s9aFaXA?si=QWZe293iTKf_3ELU

DevQuasar/deepseek-ai.DeepSeek-R1-0528-GGUF

csabakecskemeti

posted an update 2 months ago

Post

2086

Local Llama4 Maverick Q2
https://youtu.be/4F8g_LThli0?si=MGba2SUTHt6xYw3T
Quants uploading now

Big thanks to @ngxson !

csabakecskemeti

posted an update 2 months ago

Post

1725

Why the 'how many r's in strawberry' prompt "breaks" llama4? :D

Quants DevQuasar/meta-llama.Llama-4-Scout-17B-16E-Instruct-GGUF

3 replies

csabakecskemeti

posted an update 3 months ago

Post

3375

I'm collecting llama-bench results for inference with a llama 3.1 8B q4 and q8 reference models on varoius GPUs. The results are average of 5 executions.
The system varies (different motherboard and CPU ... but that probably that has little effect on the inference performance).

https://devquasar.com/gpu-gguf-inference-comparison/
the exact models user are in the page

I'd welcome results from other GPUs is you have access do anything else you've need in the post. Hopefully this is useful information everyone.

csabakecskemeti

posted an update 3 months ago

Post

2394

Managed to get my hands on a 5090FE, it's beefy

| llama 8B Q8_0 | 7.95 GiB | 8.03 B | CUDA | 99 | pp512 | 12207.44 ± 481.67 |
| llama 8B Q8_0 | 7.95 GiB | 8.03 B | CUDA | 99 | tg128 | 143.18 ± 0.18 |

Comparison with others GPUs
http://devquasar.com/gpu-gguf-inference-comparison/