ended8월 18일· 1 sources
Qwen3.8-27B at 256K on a 24GB RTX PRO 4000 SFF (432 GB/s): 50 tok/s with MTP
Why it matters
I gave Qwen3.8's MTP drafter another 69.2 MiB of precision. Throughput fell from 50.44 to 37.02 tokens per second. That result sums up the whole experiment: the best local inference setup is rarely ma...
1
Sources
+0
24h
—
Growth
7d
Active