alex
local.ai/alex
Organisations
Claimed August 2026
Bio
i like turtles
My machines
Apple M5 Max
×5PrimaryApple Silicon · 128 GB each
Recommended for MacBook Pro M5 Max 128GB · 40-core GPU
Choose what matters most
Best fit
Qwen3.6 35B A3B · UD-Q4_K_S
Best balance of speed and intelligence.
Intelligence68.5Speed17.0 tasks/hrSize20.9 GBMore intelligent
Step 3.7 Flash · IQ4_XS
2% more intelligence · 31% slower.
Intelligence70.0Speed13.0 tasks/hrSize105.0 GB
Faster
Ornith 1.0 35B · Q4_K_M
37% faster · retains 98% intelligence.
Intelligence67.2Speed27.1 tasks/hrSize21.2 GBAI Ryzen Max 395+
×2Approximate128 GB each
Approximate options
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 GBFaster
Ornith 1.0 35B · Q4_K_M
~42% faster · retains ~98% intelligence.
Intelligence67.2Speed20.8 tasks/hrSize21.2 GBApproximate for 128 GB VRAM. Results may vary.
Apple M3 Ultra
×8Apple Silicon · 512 GB each
Models larger than 128GB are not supported right now.
Recommended for Apple M3 Ultra
Choose what matters most
Best fit
Qwen3.6 35B A3B · UD-Q4_K_S
Best balance of speed and intelligence.
Intelligence68.5Speed16.7 tasks/hrSize20.9 GBMore intelligent
Qwen3.6 27B OptiQ · 4BIT
5% more intelligence · 114% slower.
Intelligence72.0Speed7.8 tasks/hrSize19.7 GBFaster
Ornith 1.0 35B · Q4_K_M
29% faster · retains 98% intelligence.
Intelligence67.2Speed23.5 tasks/hrSize21.2 GBFramework Desktop
Approximate128 GB
Approximate options
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 GBFaster
Ornith 1.0 35B · Q4_K_M
~42% faster · retains ~98% intelligence.
Intelligence67.2Speed20.8 tasks/hrSize21.2 GBApproximate for 128 GB VRAM. Results may vary.
Mac mini M4 Pro 48GB · 20-core GPU
×2Apple · 48 GB each
Recommended for Mac mini M4 Pro 48GB · 20-core GPU
Choose what matters most
Best fit
Ornith 1.0 35B · Q4_K_M
Best balance of speed and intelligence.
Intelligence67.2Speed13.8 tasks/hrSize21.2 GBMore intelligent
Qwen3.6 35B A3B · UD-Q4_K_M
2% more intelligence · 78% slower.
Intelligence68.9Speed7.7 tasks/hrSize22.1 GB
Faster
Holo 3.1 35B A3B · Q4_K_M
13% faster · retains 77% intelligence.
Intelligence52.0Speed15.8 tasks/hrSize21.3 GBMacBook Pro M4 Max · 40-core GPU
×9Apple · 48 GB each
Recommended for MacBook Pro M4 Max · 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 GBFaster
Ornith 1.0 35B · Q4_K_M
42% faster · retains 98% intelligence.
Intelligence67.2Speed20.8 tasks/hrSize21.2 GB
NVIDIA RTX PRO 6000 Blackwell 96GB
NVIDIA · 96 GB
Recommended for NVIDIA RTX PRO 6000 Blackwell 96GB
Choose what matters most
Best fit
Qwen3.6 35B A3B · NVFP4
Best balance of speed and intelligence.
Intelligence69.7Speed47.7 tasks/hrSize23.4 GBMore intelligent
Qwen3.6 27B · FP8
6% more intelligence · 86% slower.
Intelligence73.7Speed25.6 tasks/hrSize30.9 GBFaster
Ornith 1.0 35B · Q4_K_M
36% faster · retains 97% intelligence.
Intelligence67.2Speed75.0 tasks/hrSize21.2 GBNVIDIA RTX PRO 6000 Blackwell 96GB
NVIDIA · 96 GB
Recommended for NVIDIA RTX PRO 6000 Blackwell 96GB
Choose what matters most
Best fit
Qwen3.6 35B A3B · NVFP4
Best balance of speed and intelligence.
Intelligence69.7Speed47.7 tasks/hrSize23.4 GBMore intelligent
Qwen3.6 27B · FP8
6% more intelligence · 86% slower.
Intelligence73.7Speed25.6 tasks/hrSize30.9 GBFaster
Ornith 1.0 35B · Q4_K_M
36% faster · retains 97% intelligence.
Intelligence67.2Speed75.0 tasks/hrSize21.2 GBRTX 3080
NVIDIA · 24 GB
We don't have a benchmark for RTX 3080 yet.