Slavik

SlavikF's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in unsloth/Qwen3.5-397B-A17B-GGUF 6 days ago

Q3_K_XL works surprisingly fast for 3x3090 + 128 ram

🔥 8

4

#4 opened 7 days ago by

fizzacles

New activity in unsloth/Qwen3.5-397B-A17B-GGUF 8 days ago

How to choose MXFP4 vs Q4_K_XL on CPU + CUDA

2

#1 opened 8 days ago by

SlavikF

New activity in Qwen/Qwen3-Coder-Next-GGUF 11 days ago

Performance report with 2 GPUs: 85 t/s

👍 2

1

#1 opened 20 days ago by

SlavikF

New activity in stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S 16 days ago

Performance report with 72GB VRAM: 32 t/s

1

#14 opened 16 days ago by

SlavikF

chat template is broken

11

#12 opened 17 days ago by

grapevine-AI

New activity in unsloth/Qwen3-Coder-Next-GGUF 18 days ago

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

14

#2 opened 20 days ago by

RGMC98

New activity in unsloth/GLM-4.7-Flash-GGUF 27 days ago

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

🔥 2

4

#18 opened 28 days ago by

SlavikF

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

Error: Cannot set `add_generation_prompt`

1

#4 opened about 1 month ago by

SlavikF

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

🔥 1

10

#2 opened about 2 months ago by

SlavikF

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

unknown projector type: glm4v

2

#1 opened 2 months ago by

SlavikF

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

Reasoning output gets into the answer field (FIXED)

3

#6 opened 3 months ago by

SlavikF

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

how to run it?

5

#1 opened 5 months ago by

SlavikF

New activity in ilintar/Qwen3-Next-80B-A3B-Instruct-GGUF 4 months ago

Testing report on Intel Xeon W5-3425

👍 2

#2 opened 4 months ago by

SlavikF

New activity in lefromage/Qwen3-Next-80B-A3B-Thinking-GGUF 4 months ago

Testing report on Intel Xeon W5-3425

👍 1

3

#1 opened 4 months ago by

SlavikF

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

Comparing scores across many models

👍 1

#2 opened 4 months ago by

SlavikF

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

❤️ 1

#1 opened 4 months ago by

SlavikF

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

"<think>" is missing in the response!

1

#7 opened 4 months ago by

situtu

New activity in Qwen/Qwen3-VL-30B-A3B-Instruct-FP8 5 months ago

gguf quantization

4

#2 opened 5 months ago by

Pragg100510

New activity in Qwen/Qwen3-VL-30B-A3B-Thinking-FP8 5 months ago

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

👍 4

#1 opened 5 months ago by

SlavikF

New activity in Intel/Qwen3-Next-80B-A3B-Thinking-int4-AutoRound 5 months ago

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

3

#2 opened 5 months ago by

hlxxxxxx