antirez on the new DeepSeek model: 2-bit quants may not hold up, and it's not really 'local'
antirez · x · 2026-09-10
Redis creator antirez weighed in on the newly released DeepSeek model: 2-bit quantization could work as an initial experiment, but he questions whether quality and speed hold up. Generation activates far more parameters than the DS4Flash model, so it will be slower — best suited for the 512GB Mac M5 Ultra expected later this year. In his view, it's not really a 'local' model.
More from Models
- Week 3 of "Fable 5.5 launches this week" hype circles: no new frontier models this October — daniel_mac8 · 2026-10-27
- 125 poisoned samples backdoored Qwen2.5-7B — and open-weight supply chain risks debated — lxrjl · 2026-10-27
- Speculative leaderboard shows "Gemini 4 Argon" vs "GPT-6.1 Sol"; observer calls MiniMax parity suspicious — teortaxesTex · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27
- Across 7 tasks, highest reasoning setting isn't the best for most open models — keunwoochoi · 2026-10-27