Slavik's picture

27 1 1

Slavik

SlavikF

·

https://memo.fursov.family/

AI & ML interests

None yet

Recent Activity

new activity 3 days ago

stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S:Performance report with 72GB VRAM: 32 t/s

new activity 3 days ago

stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S:chat template is broken

new activity 5 days ago

unsloth/Qwen3-Coder-Next-GGUF:Error jinja template LM Studio + Open Code or Qwen code or Kilo Code

View all activity

Organizations

None yet

New activity in stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S 3 days ago

Performance report with 72GB VRAM: 32 t/s

#14 opened 3 days ago by

chat template is broken

#12 opened 3 days ago by

New activity in unsloth/Qwen3-Coder-Next-GGUF 5 days ago

Error jinja template LM Studio + Open Code or Qwen code or Kilo Code

#2 opened 6 days ago by

New activity in Qwen/Qwen3-Coder-Next-GGUF 6 days ago

Tools not working. Performance report with 2 GPUs: 85 t/s

#1 opened 6 days ago by

New activity in unsloth/GLM-4.7-Flash-GGUF 14 days ago

New flag: kv-unified. Performance report: 90 t/s on RTX 4090D 48GB

#18 opened 14 days ago by

New activity in cyankiwi/Devstral-Small-2-24B-Instruct-2512-AWQ-4bit about 1 month ago

Error: Cannot set `add_generation_prompt`

#4 opened about 1 month ago by

New activity in unsloth/MiniMax-M2.1-GGUF about 2 months ago

Report: getting 20 t/s with UD-Q4_K_XL and 72 VRAM

#2 opened about 2 months ago by

New activity in ggml-org/GLM-4.6V-GGUF about 2 months ago

unknown projector type: glm4v

#1 opened about 2 months ago by

New activity in unsloth/MiniMax-M2-GGUF 3 months ago

Reasoning output gets into the answer field (FIXED)

#6 opened 3 months ago by

New activity in cyankiwi/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit 3 months ago

how to run it?

#1 opened 4 months ago by

New activity in ilintar/Qwen3-Next-80B-A3B-Instruct-GGUF 3 months ago

Testing report on Intel Xeon W5-3425

#2 opened 3 months ago by

New activity in lefromage/Qwen3-Next-80B-A3B-Thinking-GGUF 3 months ago

Testing report on Intel Xeon W5-3425

#1 opened 3 months ago by

New activity in Qwen/Qwen3-VL-32B-Thinking-FP8 4 months ago

Comparing scores across many models

#2 opened 4 months ago by

Performance report on RTX 4090D with 48GB RAM: 16 t/s

#1 opened 4 months ago by

New activity in Qwen/Qwen3-VL-8B-Thinking 4 months ago

"<think>" is missing in the response!

#7 opened 4 months ago by

New activity in Qwen/Qwen3-VL-30B-A3B-Instruct-FP8 4 months ago

gguf quantization

#2 opened 4 months ago by

New activity in Qwen/Qwen3-VL-30B-A3B-Thinking-FP8 4 months ago

Performance report on RTX 4090D with 48GB RAM: 90 t/s

#1 opened 4 months ago by

New activity in Intel/Qwen3-Next-80B-A3B-Thinking-int4-AutoRound 4 months ago

Qwen/Qwen3-Next-80B-A3B-Thinking has MMLU_PRO 82.7 but you guys get 0.7271

#2 opened 5 months ago by

New activity in unsloth/GLM-4.6-GGUF 4 months ago

what's the best Q4 quant?

#4 opened 4 months ago by

New activity in Qwen/Qwen3-Livetranslate-Demo 5 months ago

can that demo run with any open model?

#1 opened 5 months ago by