Tim

timbuksu's activity

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

New activity in turboderp/Qwen3.8-Flash-Next-exl3 1 day ago

Benchmarked 4.05 and 5.05 bpw on 1× RTX PRO 6000 Blackwell (96 GB) + 64 GB host RAM — vs vLLM NVFP4/FP8 and vs Qwen3.8-27B

🔥 2

3

#7 opened 4 days ago by

Marzero

New activity in turboderp/Qwen3.8-Flash-Next-exl3 6 days ago

Does this support ngram nvme offloading for people with 32GB system RAM?

4

#3 opened 8 days ago by

LukeC110

New activity in primitive-ai/Qwen3.8-Flash-Next-mixed-NVFP4-FP8 6 days ago

Error when using --moe-backend marlin per the 09-03 suggestion

1

#2 opened 6 days ago by

timbuksu

New activity in RadixArk/Qwen3.8-27B-DSpark 23 days ago

Could you train one against the full-precision BF16 model?

#5 opened 23 days ago by

timbuksu

New activity in anoane/DeepSeek-V4-Flash-vllm-moet-sm120-cache about 1 month ago

Could you update this for the new DeepSeek-V4-Flash-0731 checkpoint?

2

#1 opened about 1 month ago by

timbuksu

New activity in nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451 about 2 months ago

MTP Broken & Missing MM Configs

1

#2 opened about 2 months ago by

timbuksu

New activity in huihui-ai/Huihui-DeepSeek-V4-Flash-abliterated-ds4-GGUF 3 months ago

Does not work on the newest build of antirez/ds4

6

#7 opened 3 months ago by

timbuksu

liked a model 3 months ago

froggeric/Qwen-Fixed-Chat-Templates

Updated 6 days ago • 1.63k