97 5 196

Csaba Kecskemeti PRO

csabakecskemeti

https://devquasar.com/

csabakecskemeti

AI & ML interests

None yet

Recent Activity

updated a model about 2 hours ago

DevQuasar/mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF

updated a model about 2 hours ago

DevQuasar/mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF

updated a model about 2 hours ago

DevQuasar/mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF

View all activity

Organizations

New activity in eousphoros/DeepSeek-V3.2-NVFP4 about 21 hours ago

Wondering how could you tested this with 2xRTX 6000 pro

#2 opened about 21 hours ago by

csabakecskemeti

New activity in DevQuasar/DeepSeek-V3.2-Speciale-BF16 1 day ago

bf16 version of DeepSeek-V3.2

#1 opened 1 day ago by

1245244103

New activity in DevQuasar/Qwen.Qwen3-30B-A3B-Instruct-2507-W4A16-GPTQ 5 days ago

PPL is not good

🤝 1

#1 opened 5 days ago by

snomile

New activity in DevQuasar/Qwen.Qwen3-235B-A22B-Instruct-2507-GGUF 7 days ago

imatrix?

👍 1

#1 opened 7 days ago by

Kreuz

New activity in DevQuasar/ai-sage.GigaChat3-702B-A36B-preview-bf16-GGUF 13 days ago

lol nice timing

😎 1

#1 opened 14 days ago by

ubergarm

New activity in DevQuasar/CohereLabs.command-a-translate-08-2025-GGUF 17 days ago

Has anyone got this to run?

#3 opened 18 days ago by

lbbui

New activity in DevQuasar/Qwen.Qwen3-Coder-30B-A3B-Instruct-GGUF 23 days ago

Repetition loop on Q5_K_S

#1 opened 27 days ago by

Clebio06

New activity in moonshotai/Kimi-K2-Thinking 27 days ago

Python script to decompress tensors?

➕ 🔥 2

#2 opened 28 days ago by

ubergarm

New activity in DevQuasar/MiniMaxAI.MiniMax-M2-GGUF about 1 month ago

Seems to be working with PR and `--jinja`

❤️ 🤝 3

#1 opened about 1 month ago by

ubergarm

New activity in Wan-AI/Wan2.2-S2V-14B about 1 month ago

DGX Spark prebuilds

#13 opened about 1 month ago by

csabakecskemeti

New activity in DevQuasar/Kwaipilot.KAT-V1-40B-GGUF 2 months ago

What version of llamacpp that u use to run this model?

#1 opened 4 months ago by

saipangon

New activity in DevQuasar/bigcode.starcoder2-15b-GGUF 2 months ago

The model has tendency to hallucinate for long time

#1 opened 3 months ago by

Cleanable

New activity in DevQuasar/prithivMLmods.Qwen2-VL-OCR2-2B-Instruct-GGUF 3 months ago

How to load the model?

👀 1

#1 opened 3 months ago by

Blithe8002

New activity in DevQuasar/Qwen.Qwen3-Next-80B-A3B-Instruct-FP8-Dynamic 3 months ago

Could you share your quantization code？

#1 opened 3 months ago by

traphix

New activity in DevQuasar/Qwen.Qwen3-Next-80B-A3B-Instruct-FP8 3 months ago

VLLM compatibility?

#1 opened 3 months ago by

aidendle94

New activity in DevQuasar/CohereLabs.command-a-translate-08-2025-GGUF 3 months ago

so, how did it do?

#2 opened 3 months ago by

robbiemu

Request for BF16 GGUF

👍 1

#1 opened 3 months ago by

GeorgyGUF

New activity in DevQuasar/Qwen.Qwen3-Reranker-4B-GGUF 4 months ago

please provide code for gguf'ing for 0.6b or 4b

#1 opened 4 months ago by

mansurealism

New activity in DevQuasar/openai.gpt-oss-20b-GGUF 4 months ago

GPT-OSS-20B (GGUF) running on RTX A5000 24GB with llama.cpp — thank you, DevQuasar! 🙌

👍 1

#1 opened 4 months ago by

Guaranta

New activity in gabriellarson/gpt-oss-20b-GGUF 4 months ago

what can run this?

#1 opened 4 months ago by

csabakecskemeti

Csaba Kecskemeti PRO

AI & ML interests

Recent Activity

Organizations

csabakecskemeti's activity

Wondering how could you tested this with 2xRTX 6000 pro

bf16 version of DeepSeek-V3.2

PPL is not good

imatrix?

lol nice timing

Has anyone got this to run?

Repetition loop on Q5_K_S

Python script to decompress tensors?

Seems to be working with PR and `--jinja`

DGX Spark prebuilds

What version of llamacpp that u use to run this model?

The model has tendency to hallucinate for long time

How to load the model?

Could you share your quantization code？

VLLM compatibility?

so, how did it do?

Request for BF16 GGUF

please provide code for gguf'ing for 0.6b or 4b

GPT-OSS-20B (GGUF) running on RTX A5000 24GB with llama.cpp — thank you, DevQuasar! 🙌

what can run this?