Tech2Wild
@Tech2Wild
๐ฎ Tech, gaming, AI, and everything in between. ๐ค Building with it, not just talking about it. ๐ฅ From the mind of @ToNYD2WiLD
๊ฐ์
March 2026
222 ํ๋ก์ ์ค 4.8K ํฌ
GLM 5.3 Flash on 4 DGX Sparks with TensorFold ๐ฅ
vs my vLLM TP4 stack, same harness:
โก Code 127 vs 120 tok/s
โก JSON 133 vs 120
๐ ๏ธ Tool calls 93 vs 68 (+37%)
๐ Faster at every concurrency, C1 to C6
๐ 500K-token prompt in 191s (vLLM 202s)
๐ง 8 streams, 500K context each, vision on
๋ ๋ณด๊ธฐ
