Nah, maybe in us of a, you get epic clown show going on. World is bigger. There will be places. You cans stop open source. Learned from pgp story. The question though about data, training. Arch advances are super solid.
0rand
21
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Gemma 4 Day-1 Inference on NVIDIA DGX Spark — Preliminary Benchmarks | 17 | 11750 | April 7, 2026 | |
| New bleeding-edge vLLM Docker Image: avarok/vllm-nvfp4-gb10-sm120 | 32 | 4007 | December 17, 2025 | |
| Gemma 4 Models - which vLLM version? Any PRs spotted? | 177 | 16642 | April 16, 2026 | |
| Qwen3.5-122B-A10B NVFP4 Quantized for DGX Spark — 234GB → 75GB, Runs on 128GB | 44 | 14150 | April 9, 2026 | |
| Custom built vLLM + Qwen3.5-35B on NVIDIA DGX Spark (GB10) — sustained 50 tok/s, 1M context | 18 | 5379 | May 7, 2026 | |
| Serving Qwen3.5-397B-A17B at 1M Tokens on 2× DGX Spark — MiniMax M3 Is Next | 5 | 1539 | July 3, 2026 | |
| Best Q4 / NVFP4 model for quality Qwen3.5-27B or alternatives? | 16 | 5811 | April 26, 2026 | |
| We unlocked NVFP4 on the DGX Spark: 20% faster than AWQ! | 144 | 13236 | March 14, 2026 | |
| Qwen3.8-27B-NVFP4 on a single DGX Spark — up to 1M context, vLLM+MTP measurements | 25 | 16600 | August 20, 2026 | |
| Update for NVFP4 Model conversion to use W4A16 instead of W4A4 | 0 | 864 | May 17, 2026 |