pathosethoslogos
pathosethoslogos
·
AI & ML interests
None yet
Recent Activity
new activity 3 days ago
z-lab/Qwen3.6-27B-DFlash:Would this work with the FP8 version of the model? new activity 4 days ago
deepseek-ai/DeepSeek-V4-Pro:I'm very disappointed in this release new activity 5 days ago
sgl-project/DeepSeek-V4-Flash-FP8:Double the size of the original?Organizations
None yet
Would this work with the FP8 version of the model?
3
#5 opened 3 days ago
by
pathosethoslogos
I'm very disappointed in this release
🔥➕ 13
11
#131 opened 5 days ago
by
Dampfinchen
Double the size of the original?
3
#3 opened 5 days ago
by
pathosethoslogos
[Question] Can the model be run on Nvidia DGX Spark?
2
#2 opened 7 days ago
by
hubertshelley
SGLang --speculative-algorithm NEXTN or EAGLE?
👍 1
#6 opened 6 days ago
by
pathosethoslogos
[redacted]
1
#1 opened 6 days ago
by
pathosethoslogos
Is have Qwen3.6 35B A3B FP8 version?
➕ 1
1
#4 opened 7 days ago
by
whaozl
Model quant requests?
1
#1 opened 8 days ago
by
pathosethoslogos
Model request?
2
#1 opened 12 days ago
by
pathosethoslogos
CUDA version 13?
1
#1 opened 24 days ago
by
pathosethoslogos
This model goes crazy and goes on an infinite loop often
1
#2 opened 24 days ago
by
pathosethoslogos
'Customer Docker image' ... where?
2
#3 opened about 1 month ago
by
pathosethoslogos
Does anyone know a good 4 bit quant version?
#46 opened about 2 months ago
by
pathosethoslogos
Redacted
#9 opened about 2 months ago
by
pathosethoslogos
Do you take quant requests?
1
#1 opened about 2 months ago
by
pathosethoslogos
Qwen Team :- Qwen3-coder-next vs Qwen3.5-35B-A3B for coding
2
#29 opened 2 months ago
by
mayankiit04
Really loving the idea behind this model
3
#3 opened 2 months ago
by
pathosethoslogos
Infinite loop every prompt
👀 1
2
#2 opened about 2 months ago
by
pathosethoslogos
Model requests?
12
#4 opened 2 months ago
by
pathosethoslogos
Why is this 111B parameters instead of the original 199B? Is it REAPed?
1
#2 opened 2 months ago
by
pathosethoslogos