Qwen 3.6 NVFP4 Real World Tokens on RTX 4090
First test was done with 60,000 context window. Test #2 was done with 5,000 context window. The first test got about 8 Tokens/Second. Test 2 got about 15 Tokens/Second. Full specs of my PC: CPU: AMD Ryzen 7 7800x3D, RAM: G Skill 32GB DDR5, GPU: Gigabyte RTX 4090 XTREME WATERFORCE, SSD: TEAMGROUP 4TB T-Force CARDEA Zero Z44Q
▶︎
China Just Won The AI Race
▶︎
The Local AI Hardware Mistake Everyone Makes
▶︎
This Is The Real Reason Nvidia Abandoned PC Gamers
▶︎
I Hacked This Temu Router. What I Found Should Be Illegal.
▶︎
AMD Finally Built a DGX Spark Rival… But Something’s Off
▶︎
Ego Bodybuilder HUMILIATED Beyond Belief 🤯 | Anatoly GYM PRANK
▶︎
Is This DIY EMP Device Actually Dangerous?
▶︎
This radio can see through walls
▶︎
LAWYER: If Cops Ask "Where Are You Coming From?" - Say These Words
▶︎
Shor's Algorithm for Quantum Computing - Computerphile
▶︎
"Chrupalla isn't the sharpest tool in the shed!" Stegner's last brain cells are failing.
▶︎
Don't Hang Up On AI Scammers. Do THIS Instead.
▶︎
Android 17 sucks. So I put Linux on a phone.
▶︎
The Deadliest Weapon of the Ancient World
▶︎
Nvidia Tried to Stop This... 2X VRAM GPU Mod
▶︎
AI Bubble: ‘This could actually be lethal | Ed Zitron
▶︎
Creating a 48GB NVIDIA RTX 4090 GPU | Brother Zhang's Repair Shop (ft. 张哥)
▶︎
Zig 2026: No-AI Policy, $670K Foundation, Left GitHub & Why Zig Isn’t 1.0 - Andrew Kelley Explains
▶︎
AMD MI50 32GB for Local AI: Qwen 3.6 & Gemma 4 on llama.cpp / vLLM (vs R9700)
▶︎