Qwen 3.8 27b NVFP4 inside TensorFold native CLI on Windows 11 cooking on a nvidia RTX 5090.
🤯 Single-stream decode was ~220 tps for prose. Prefill was ~12,200 tps C=4 was over 500 tps decode. Will be in the next engine release 👌🏼
20M Tokens FREE Every Day on APInex_AI🆓
The promo continues. Use your 20M daily allowance on top models: 1️⃣ DeepSeek V4.1 Flash 1017 2️⃣ Kimi K3 3️⃣ Qwen 3.8 MAX 4️⃣ GLM 5.3 Flash 5️⃣ Gemini 3.8 Flash ⚡️ Works in Cursor, Claude Code, Hermes and OpenCode 👉
DeepSeek 4.1 Flash vs Qwen 3.8 27B vs minimax H3 lol 😂
H3 results 👇
A Qwen 3.8 27B on one Mac Studio beside DeepSeek on my four box Spark cluster.
Same harbor prompt. Qwen: 53.57 tokens/sec. DeepSeek: 107.70. IMO, both models are doing phenomenally with good fine tuning. Both demos had two correction rounds plus manual visual repairs. Speeds
You have reached the end of the archive
All of qwen38