Span Spek
spanspek
AI & ML interests
None yet
Recent Activity
new activity about 21 hours ago
nvidia/NVIDIA-Nemotron-Labs-3-Competitive-Coding-550B-A55B-NVFP4:Scores on DeepSWE and Terminal Bench 4.0? liked a model 2 days ago
NaiveAI/Naive-N0.5-Flash liked a model 6 days ago
XingChen-AGI/TeleOCROrganizations
None yet
Scores on DeepSWE and Terminal Bench 4.0?
#1 opened about 21 hours ago
by
spanspek
can add gguf for us, please?
👍 3
4
#1 opened 28 days ago
by
xizonghu
🚩 Report: Spam
👍 6
6
#2 opened 13 days ago
by
spanspek
Number on graphics in README are difficult to read
1
#16 opened 16 days ago
by
spanspek
Quant request - FP8
#2 opened 21 days ago
by
spanspek
failed on llama.cpp (GGML_ASSERT)
4
#1 opened about 1 month ago
by
mahdisml
qwen3.8-27b on one pro 6000: 140 tok/s, day after release
7
#101 opened about 2 months ago
by
Avifenesh
Making sense of the graph
❤️👍 2
1
#2 opened about 1 month ago
by
spanspek
🚩 Report: Spam
😔👍 10
4
#5 opened about 1 month ago
by
spanspek
Model name looks incorrect
👍 3
3
#2 opened about 1 month ago
by
spanspek
Question on Q6 and Q8
2
#1 opened about 2 months ago
by
spanspek
Request for FP8
5
#5 opened about 2 months ago
by
spanspek
🚩 Report: Spam
1
#2 opened about 2 months ago
by
spanspek
This is not Qwen3.8
👍 1
2
#1 opened about 2 months ago
by
zzdave
Awww yiss
🚀🔥 26
10
#1 opened 2 months ago
by
CurbStomper
Any plans for FP8?
2
#5 opened 2 months ago
by
spanspek
OvisOCR2 vs Gemma-4-E4B vision encoder?
1
#2 opened 3 months ago
by
Daankular
The Q1_0 is phenomenal
🤝🔥 2
7
#2 opened 3 months ago
by
spanspek
🚩 Report: Spam
#2 opened 3 months ago
by
spanspek
...
1
#9 opened 3 months ago
by
ShayanShamsi