maxwell-model/Maxwell-V1-Flash
text-generation · ♥ 341 · ↓ 3.3K
- Tasktext-generation
- Downloads2453
- Likes302
- Licenseapache-2.0
text-generation · ♥ 341 · ↓ 3.3K
Maxwell-V1.0-Flash is a next-generation, high-performance Mixture-of-Experts (MoE) language model developed by the Maxwell Team, with **35B total parameters and 3B active parameters per token** (both excluding embeddings) and support for context lengths up to 256K tokens. It is designed for strong reasoning, agentic, and long-context capabilities at a practical inference cost.
Pre-training. Approximately 26T tokens of multilingual data, with the Muon optimizer on most hidden weight matrices. Training starts dense; block-sparse attention enters at 128K mid-training, once the indexer is warmed up against dense full-history attention, then trains jointly with the backbone.
Excerpt from the model card on Hugging Face ↗.
maxwell-model/Maxwell-V1-Flash was first seen on Hugging Face · Trending models on Nov 17, 2026. Since then it has appeared in 126 checks on 6 different days. Its best position was #6 of 30, reached on Nov 20, 11:45 UTC. It is #17 right now, holding steady at #17 over the last 6 checks.
Position on Hugging Face · Trending models at every check (lower is better).
Best rank per day (UTC).
🔥 as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 22, 16:45 UTC it is #17, holding steady at #17 over the last 6 checks.
#6 on Hugging Face · Trending models, on Nov 20, 11:45 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 17, 2026 and has been on the list on 6 days (126 checks) since.
It is tagged text-generation on Hugging Face and has 2453 downloads under the apache-2.0 license.