Laguna 2.1 Launch Sparks Mac Acceleration Race

Episode 1 · Laguna S 2.1 Released: 6% Size Outperforms DeepSeek V4 Pro, MLX.fast Competition Launched (2026-07-28, 8 posts)

Laguna S 2.1 has been officially released, with the team claiming it is only 6% the size of DeepSeek V4 Pro yet delivers higher performance. This 100B parameter open-weight model can already run locally on a 128GB MacBook. To promote edge deployment of the same-architecture Laguna XS 2.1, the team, in collaboration with Poolside and EigenLabs, launched the MLX.fast public competition, encouraging developers to optimize inference speed on Apple Silicon consumer Macs. The model already runs on Mac, and internal tests achieved a 36.8% speedup within 24 hours.

Confirmed

• Laguna S 2.1 is 6% the size of DeepSeek V4 Pro and offers higher performance.
• Laguna S/XS 2.1, approximately 100B parameters, runs locally on a 128GB MacBook.
• The team internally achieved a 36.8% speedup for Laguna in 24 hours, with further room for improvement.
• Poolside, EigenLabs, and MLX.fast launched a public competition to further accelerate Laguna XS 2.1 inference on consumer Macs.

Why it matters

• Small model, high performance: If verified, the 6% size with superior performance could significantly lower the compute barrier for AI inference.
• Edge inference optimization: The open-source competition for Apple Silicon Macs helps promote complex models on consumer hardware and local deployment.
• Benchmark anti-cheat: The team is strengthening the verifier harness to reduce cheating, and experimenting with a continuous open improvement mechanism allowing participants to contribute agent progress, offering a new reference for fair AI performance evaluation.

• Laguna S 2.1 claims 6% of DeepSeek V4 Pro’s size with higher performance — gajesh · 2026-07-28
• Laguna says it sped up 36.8% in 24 hours and is opening benchmark improvement — gajesh · 2026-07-28
• Laguna gets 36.8% faster in 24 hours as its benchmark harness is hardened — gajesh · 2026-07-28
• Open competition targets 36.8% faster Laguna XS 2.1 inference on consumer Macs — gajesh · 2026-07-28
• Laguna S 2.1 gets a Mac-speed push with MLX.fast optimization contest — gajesh · 2026-07-28
• Poolside and EigenLabs launch an open contest to speed up Laguna XS 2.1 on Apple Silicon Macs — gajesh · 2026-07-28
• MLX.fast opens a public competition to make Laguna XS 2.1 run faster on consumer Macs — gajesh · 2026-07-28
• Poolside says its 100B open-weight model runs on a 128GB MacBook — gajesh · 2026-07-28

Episode 2 · Open Source Community Boosts Mac LLM Inference Speed by Over 80% (2026-07-30, 2 posts)

In just 24 hours, the open-source community achieved a breakthrough in the Mac inference optimization challenge for the Laguna XS 2.1 model. Without using speculative decoding, they successfully boosted inference speeds by 80.6%.

• Open Community Boosts Local LLM Inference on Mac by 80.6% Without Speculative Decoding — gajesh · 2026-07-30
• Mac Inference Speed Surges 80% as Open Source Community Breaks Performance Limits — gajesh · 2026-07-30