Łukasz Różewicz PRO

wiklif's activity

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

liked a model about 11 hours ago

bottlecapai/ThinkingCap-Qwen3.8-27B

Image-Text-to-Text • 28B • Updated about 15 hours ago • 128 • 88

liked a model 2 days ago

convaiinnovations/laya

Text Classification • 0.4B • Updated about 24 hours ago • 3.45k

updated a model 9 days ago

wiklif/Qwen3.8-27B-KTopt-GGUF

Text Generation • 16.2M • Updated 9 days ago • 1.04k • 4

liked a model 11 days ago

wiklif/Qwen3.8-27B-KTopt-GGUF

Text Generation • 16.2M • Updated 9 days ago • 1.04k • 4

published a model 12 days ago

wiklif/Qwen3.8-27B-KTopt-GGUF

Text Generation • 16.2M • Updated 9 days ago • 1.04k • 4

New activity in zai-org/GLM-5.3-Flash 12 days ago

GLM-5.3-Flash runs great on a single, regular DGX Spark (vLLM, 200K context, HumanEval 97%)

❤️ 1

#50 opened 12 days ago by

wiklif

liked a model about 2 months ago

deepseek-ai/DeepSeek-V4-Flash-0731

Text Generation • 304B • Updated Aug 1 • 3.71M • • 4.01k

New activity in deepseek-ai/DeepSeek-V4-Flash-0731 about 2 months ago

Running 0731 on a single DGX Spark (GB10, 128GB) - working vLLM config, 256K context

❤️👍 6

8

#32 opened about 2 months ago by

wiklif

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 2 months ago

For DGX Spark (GB10) owners: a vLLM alternative to GGUF with the native DSpark speculative head - ~10 tok/s, 256K ctx, tool calling

2

#22 opened about 2 months ago by

wiklif

New activity in RedHatAI/DeepSeek-V4-Flash-speculator.dflash about 2 months ago

Request: variant trained against DeepSeek-V4-Flash-0731 (different weights - acceptance collapses to ~3%)

#1 opened about 2 months ago by

wiklif