ringo

salted-user's activity

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

New activity in XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B about 1 month ago

GGUF/llama.cpp results: YaRN 512K works: 40/40 needle retrieval at 512K, zero short-task quality loss, ~660 tok/s prefill (llama.cpp, RX 7900 XTX)

👍 1

1

#13 opened about 1 month ago by

salted-user

liked a model about 1 month ago

kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF

Text Generation • 27B • Updated Sep 1 • 3.07k • 9

New activity in kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF about 1 month ago

First quality numbers for Uncensored-FAST: MMLU-Pro 75.7 / GPQA 56.6 / LCB 62% — plus a thinking-budget heads-up

#2 opened about 1 month ago by

salted-user

liked 2 models about 1 month ago

XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B

Image-Text-to-Text • 9B • Updated 13 days ago • 19.6k • 699

bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF

Image-Text-to-Text • 9B • Updated Sep 21 • 980k • 191

New activity in bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF about 1 month ago

YaRN 512K works: 40/40 needle retrieval at 512K, zero short-task quality loss, ~660 tok/s prefill (llama.cpp, RX 7900 XTX)

👍 1

#6 opened about 1 month ago by

salted-user