gated
livepeer-ren
AI & ML interests
None yet
Recent Activity
new activity about 19 hours ago
sakamakismile/Qwen3.6-27B-Text-NVFP4-MTP:RTX5090 performence and setup new activity 14 days ago
RedHatAI/Qwen3.6-35B-A3B-NVFP4:Qwen3.6-27B?Organizations
None yet
RTX5090 performence and setup
2
#14 opened 3 days ago
by
jasionkajakub
Issue with Agentic Coding / Tool Calling - Model Hangs
4
#2 opened 16 days ago
by
ByDiavolos
Qwen3.6-27B?
➕ 5
2
#8 opened 22 days ago
by
alexcardo
SGLang --speculative-algorithm NEXTN or EAGLE?
👍 2
1
#6 opened about 1 month ago
by
pathosethoslogos
16Gb VRAM not enough even for small context
16
#10 opened 24 days ago
by
redval
errors with openclaw tool calls.
5
#2 opened 27 days ago
by
kraka40
Broken chat_template tool calling and thinking
14
#9 opened 29 days ago
by
livepeer-ren
function_call do not give me report usually
2
#27 opened 28 days ago
by
HeisenbergQ
Very buggy in vllm + opencode
👀 1
2
#40 opened about 1 month ago
by
void009
--enable-prefix-caching and Feedback from HGX B200 Deployment
2
#5 opened about 1 month ago
by
cgelias
Does it support tool calling?
2
#4 opened about 1 month ago
by
xing120226
Great quant!!
12
#6 opened about 1 month ago
by
tasticleeze
Missing Another Trick?
2
#3 opened about 1 month ago
by
odorizhou
Qwen3.6-27B-NVFP4 is slower than official FP8 on Blackwell; possible fallback / FLA path mismatch on vLLM
👀 2
8
#5 opened about 1 month ago
by
garrussun
MTP not responding
9
#7 opened about 1 month ago
by
joelafrite
claude code
2
#6 opened about 1 month ago
by
chrisqianz
sglang
1
#4 opened about 1 month ago
by
livepeer-ren
Cant be authenticated to use the model.
1
#14 opened about 2 years ago
by
livepeer-ren