|
Crucible LLM :: Bench your LLM and server. Is it fast enough… for everyone?
|
|
21
|
407
|
October 11, 2026
|
|
Making Qwen 3.8 27B fast on Strix Halo gfx1151
|
|
24
|
3009
|
October 11, 2026
|
|
Quad R9700's on AM4 Shenanigans
|
|
77
|
1097
|
October 10, 2026
|
|
Model performance on the Radeon VII
|
|
4
|
255
|
October 7, 2026
|
|
Home AI GPU upgrade
|
|
10
|
370
|
October 5, 2026
|
|
Local LLM Based Coding on HPC Equipment
|
|
26
|
841
|
October 5, 2026
|
|
Provisioning Spec for Air-Gapped, Host-Isolated Local LLM Tooling
|
|
5
|
197
|
September 20, 2026
|
|
AI inference system recommendations: 8x R9700 vs 2x DGX Spark
|
|
10
|
385
|
September 5, 2026
|
|
Qwen 3.8 181B AWQ on quad R9700's
|
|
0
|
305
|
September 5, 2026
|
|
V100 four card baseplate from aliexpress
|
|
1
|
210
|
August 28, 2026
|
|
Sanity check my Qwen3.8 5090 Results; new to Local AI
|
|
7
|
489
|
August 24, 2026
|
|
One week of Local AI on Strix Halo
|
|
6
|
773
|
August 23, 2026
|
|
[Solved] Help getting Odysseus up and running
|
|
1
|
118
|
August 23, 2026
|
|
US to leave open weight/open source Ai models alone
|
|
6
|
196
|
August 10, 2026
|
|
vLLM 0.23.x / ROCm 7.14 upgrade on 4x Radeon AI PRO R9700: ~50% regression on one model, unaffected on another, but a free +9% via kernel tuning
|
|
3
|
640
|
August 9, 2026
|
|
AI GPU+CPU Bottleneck
|
|
15
|
419
|
August 3, 2026
|