Sean Werner
darkstar3537
AI & ML interests
None yet
Recent Activity
new activity
1 day ago
vincentzed-hf/Qwen3.5-397B-A17B-NVFP4:Anyone try this on 4x RTX 6000 Pro yet? new activity
4 days ago
nvidia/Qwen3.5-397B-A17B-NVFP4:Support SM120 new activity
10 days ago
lukealonso/MiniMax-M2.5-NVFP4:Thanks for your effort Organizations
None yet
Anyone try this on 4x RTX 6000 Pro yet?
52
#1 opened 9 days ago
by
zenmagnets
Support SM120
❤️ 👍 15
5
#2 opened 4 days ago
by
darkstar3537
Thanks for your effort
5
#5 opened 10 days ago
by
darkstar3537
Great Model but not accessible anymore
➕ 🔥 4
8
#17 opened 13 days ago
by
darkstar3537
Accessing LLM, response without<think>start tag
5
#2 opened about 2 months ago
by
sudage
Cant run with tp 4
9
#5 opened 23 days ago
by
darkstar3537
AWQ
🤝 2
#3 opened 23 days ago
by
darkstar3537
4.6V Please
#6 opened about 1 month ago
by
darkstar3537
Great Model! - sglang mtp support for triton backend
👍 3
4
#19 opened 2 months ago
by
chriswritescode
REAP AWQ
➕ 1
1
#4 opened about 1 month ago
by
darkstar3537
How to use CPU Offload for this model? I keep getting OOM
1
#4 opened 3 months ago
by
crystech
Claude Code?
#3 opened about 2 months ago
by
darkstar3537
Duplicate files
➕ 1
7
#3 opened 3 months ago
by
darkstar3537
Quickly degrades
29
#3 opened 4 months ago
by
ehartford
AWQ Please
2
#18 opened 4 months ago
by
darkstar3537
Quantization code
1
#1 opened 4 months ago
by
bullerwins
2.25 bpw perplexity
20
#2 opened 5 months ago
by
malamen4
400 error with qwen-code
1
#2 opened 7 months ago
by
darkstar3537
72B variant
➕ 1
1
#23 opened 7 months ago
by
darkstar3537
How do I separate the reasoning from the reply?
1
#7 opened 8 months ago
by
Lockout