|
Quad R9700's on AM4 Shenanigans
|
|
86
|
1532
|
October 17, 2026
|
|
Gotcha of the day: preserve_reasoning on local backends vs. framework overrides
|
|
2
|
103
|
October 15, 2026
|
|
Making Qwen 3.8 27B fast on Strix Halo gfx1151
|
|
25
|
3276
|
October 15, 2026
|
|
Local LLM Based Coding on HPC Equipment
|
|
32
|
1028
|
October 14, 2026
|
|
Crucible LLM :: Bench your LLM and server. Is it fast enough… for everyone?
|
|
23
|
526
|
October 12, 2026
|
|
Language Model on a $19 Graphics Card
|
|
1
|
158
|
October 12, 2026
|
|
Model performance on the Radeon VII
|
|
4
|
270
|
October 7, 2026
|
|
Home AI GPU upgrade
|
|
10
|
402
|
October 5, 2026
|
|
Provisioning Spec for Air-Gapped, Host-Isolated Local LLM Tooling
|
|
5
|
206
|
September 20, 2026
|
|
AI inference system recommendations: 8x R9700 vs 2x DGX Spark
|
|
10
|
434
|
September 5, 2026
|
|
Qwen 3.8 181B AWQ on quad R9700's
|
|
0
|
326
|
September 5, 2026
|
|
V100 four card baseplate from aliexpress
|
|
1
|
222
|
August 28, 2026
|
|
Sanity check my Qwen3.8 5090 Results; new to Local AI
|
|
7
|
500
|
August 24, 2026
|
|
One week of Local AI on Strix Halo
|
|
6
|
809
|
August 23, 2026
|
|
[Solved] Help getting Odysseus up and running
|
|
1
|
125
|
August 23, 2026
|
|
US to leave open weight/open source Ai models alone
|
|
6
|
199
|
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
|
664
|
August 9, 2026
|
|
AI GPU+CPU Bottleneck
|
|
15
|
428
|
August 3, 2026
|