9 2 61

Csaba Kecskemeti PRO

csabakecskemeti

https://devquasar.com/

csabakecskemeti

AI & ML interests

None yet

Recent Activity

Reacted to cappuch's post with 😎 12 minutes ago

p104-100s are beasts. 8 gigs of VRAM, 12 tok/s on qwen 14b at q4, and 18 tok/s on 7b at q6. best thing - 20 euros each. https://furry.engineer/@cappuch/113500349547803802

posted an update 14 minutes ago

Repurposed my older AI workstation to a homelab server, it has received 2xV100 + 1xP40 I can reach huge 210k token context size with MegaBeam-Mistral-7B-512k-GGUF ~70+tok/s, or run Llama-3.1-Nemotron-70B-Instruct-HF-GGUF with 50k Context ~10tok/s (V100 only 40k ctx and 15tok/s). Also able to Lora finetune with similar performace as an RTX3090. It moved to the garage to no complaints for the noise from the family. Will move to a Rack soon :D

updated a model about 7 hours ago

DevQuasar/Isotonic.reasoning-llama3.2-3b-GGUF

View all activity

Organizations

csabakecskemeti's activity

liked a model 2 days ago

sarpba/whisper-base-hungarian_v1

Automatic Speech Recognition • Updated Oct 20 • 106 • 3

liked a dataset 4 days ago

MaziyarPanahi/orca-agentinstruct-1M-v1-cleaned-fixed-sharegpt

Viewer • Updated 4 days ago • 1.05M • 59 • 4

liked a model 12 days ago

imnotednamode/mochi-1-preview-mix-nf4-small

Updated 12 days ago • 120 • 7

liked 2 models 19 days ago

DevQuasar/amd.AMD-OLMo-1B-SFT-GGUF

Text Generation • Updated 16 days ago • 161 • 1

DevQuasar/nvidia.Llama-3.1-Nemotron-70B-Instruct-HF-GGUF

Updated Oct 19 • 1.52k • 1

liked 5 models 20 days ago

liked a model 23 days ago

facebook/MobileLLM-1B

Text Generation • Updated 22 days ago • 9.48k • 108

liked a dataset 24 days ago

Anthropic/persuasion

Viewer • Updated Apr 9 • 3.94k • 419 • 175

liked a model 27 days ago

DevQuasar/CohereForAI.aya-expanse-8b-GGUF

Updated 29 days ago • 456 • 2

liked 5 models about 1 month ago

deepseek-ai/Janus-1.3B

Any-to-Any • Updated 9 days ago • 5.6k • 462

BAAI/Emu3-Gen

Any-to-Any • Updated Oct 23 • 7.48k • 188

h2oai/h2ovl-mississippi-800m

Text Generation • Updated 8 days ago • 15.1k • 24

afrideva/llama3_8b_chat_brainstorm-GGUF

Text Generation • Updated May 13 • 42 • 1

nvidia/Llama-3_1-Nemotron-51B-Instruct

Text Generation • Updated Oct 13 • 140k • 194

liked 2 models about 2 months ago

h2oai/deberta_finetuned_pii

Token Classification • Updated Aug 3 • 1.82k • 3

nvidia/NVLM-D-72B

Image-Text-to-Text • Updated Oct 18 • 15.8k • 739