FatherTimeLine (@Father_TimeLine) header
FatherTimeLine (@Father_TimeLine) profile picture

Truth and opinions never occupy the same space.

Joined November 2025
Replying to @CARandDRIVER
The 80's Courier all over again.
2
4
757
Qwen-Next Vision q2_0 v4 one shot prompt ->-> ~73 minutes
1
3
258
Qwen-Next q2_0 v4 prompt ->-> ~36 minutes
4
278
If you think Strata is fast, Think again. @coldniko HyperCore-Tune is a drop in Optuna Tuner that will produce the perfect tune for Strata on your hardware. --eng tok/s MAX --prefill tok/s MAX --latency ms MIN max_run<model>.sh max_run<model>.json github.com/hypercoreiai/Hype…
2
1
10
871
HyperCore-CPP is running a 120B parameter model on 2.8 GB RAM With 13000+ Experts loaded in VRAM!!! github.com/hypercoreiai/Hype…
1
62
Thinking faster is getting easier with Tier 1 decode speeds.github.com/hypercoreiai/Hype…
17
Replying to @sadluck
Niko has Unleashed the KRAKEN.
1
26
Replying to @drdanielbender
here i am complaining about 220+ tok/s with a 120B model.
1
1
48
Replying to @coldniko
1 RTX 4090
1
2
177
github.com/hypercoreiai/Hype… Run the Big GGUF models on consumer grade hardware.
1
1
82
Replying to @_m0se_
3800 prefill on a single GPU
1
62
Free Model end points on Nvidia: Kimi, Deepseek, Nemetron, GLM, ... They are unlimited use and current. build.nvidia.com/explore/dis…
1
1
62
300 tokens per second on a single GPU running a 120B parameter model. The world of opensource models is a growing threat to subscription based models. That is why they want regulation.
1
17
Nobody asks how the cat got in the well. We just assume it's a problem to fix. Meanwhile the cat's probably thinking this is just a weird day. We build wells, then act surprised when something falls in. That's the whole story.
13
QWEN-Next 120B parameter model running on a single GPU. The model is clocking over 200 toks/s while reverse engineering a website. It was successful where earlier versions of GROK failed. What a time to be alive, a local model with this power is a threat to subscription models.
1
56
QWEN-Next 120 Billion parameter model running on a single GPU. The model solved a combinatorial state space that expands exponentially (6! × 6! × 6! = 373,248,000 possible permutations). What a time to be alive, a local model with this power is a threat to subscription models.
1
1
214
This what truly scary AI looks like.
1
1
383
A Massachusetts mother accused of strangling her two young children inside their home before fleeing to Vermont asked a judge to release her from custody and throw out the case. -GP
38
Replying to @Hammernecker
Jessica Rabbit?
1
2
45