VIPV2EX
local.ai/v2ex
Claimed August 2026
Bio
working on https://github.com/livid/exe
follow me on x https://x.com/Livid
My machines
RTX 5090
PrimaryGPU · 32 GB
Recommended for NVIDIA GeForce RTX 5090 32GB
Choose what matters most
Best fit
Gemma 4 31B It · AWQ-4BIT
Best balance of speed and intelligence.
Intelligence53.8Speed70.5 tasks/hrSize20.9 GBMore intelligent
Qwen3.6 35B A3B · UD-IQ4_XS
27% more intelligence · 22% slower.
Intelligence68.3Speed58.0 tasks/hrSize17.7 GB
Faster
Holo 3.1 35B A3B · NVFP4
15% faster · retains 99% intelligence.
Intelligence53.0Speed83.1 tasks/hrSize23.7 GB
Apple M4 Max
Apple Silicon · 128 GB
Recommended for MacBook Pro M4 Max 128GB · 40-core GPU
Choose what matters most
Best fit
Qwen3.6 35B A3B · UD-Q4_K_M
Best balance of speed and intelligence.
Intelligence68.9Speed12.1 tasks/hrSize22.1 GBMore intelligent
Qwen3.6 27B OptiQ · 4BIT
5% more intelligence · 109% slower.
Intelligence72.0Speed5.8 tasks/hrSize19.7 GB
Faster
Ornith 1.0 35B · Q4_K_M
42% faster · retains 98% intelligence.
Intelligence67.2Speed20.8 tasks/hrSize21.2 GB
GB10
GPU · 128 GB
RTX 6000 Ada
×2GPU · 48 GB each
Recommended for NVIDIA RTX 6000 Ada 48GB
Choose what matters most
Best fit
Ornith 1.0 35B · Q4_K_M
Best balance of speed and intelligence.
Intelligence67.2Speed51.4 tasks/hrSize21.2 GBMore intelligent
Qwen3.6 35B A3B · NVFP4
4% more intelligence · 13% slower.
Intelligence69.7Speed45.4 tasks/hrSize23.4 GBFaster
Holo 3.1 35B A3B · NVFP4
23% faster · retains 79% intelligence.
Intelligence53.0Speed66.9 tasks/hrSize23.7 GB