Qwen3.8 Max reportedly hits 2.4T parameters
Scobleizer · x · 2026-07-20
Alibaba’s Qwen3.8 Max is being described as a 2.4T-parameter open-source model that supposedly rivals Fable 5 on Alibaba’s own benchmarks.
The post frames it as a reminder that frontier-scale open models keep getting larger, but benchmark wins don’t automatically translate into affordable production inference. It also notes that Kimi K3 reportedly hit GPU capacity within 48 hours at 2.8T parameters, and Qwen3.8 is already available for testing.
Related event: Leaked Alibaba Qwen 3.8 Max Shows Strong Benchmark and Coding Performance(6 posts)→
More from Models
- Fern's "context is intelligence" thesis: prediction keeps improving out to 10.2M tokens — bneyshabur · 2026-10-26
- Mirendil launches Fern, a from-scratch pretrained model with up to 10M-token context — bneyshabur · 2026-10-26
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26