Model Optimization

62 summarised stories about Model Optimization, each linking back to the original source. Browse all topics →

Key players

Hugging Face OpenAI Anthropic NVIDIA Apple Google

Thursday, 30 July 2026

TurboFieldfare

GitHub 2 months ago 55

TurboFieldfare is a Swift and Metal runtime that runs Google's Gemma 4 26B language model in approximately 2 GB of RAM on Apple Silicon Macs by streaming expert weights from SSD rather than loading the full 14.3 GB model into memory. The system achieves 5.1–6.3 tokens per second on an 8 GB M2 MacBook Air and 31–35 tokens per second on a 24 GB M5 Pro by keeping only a 1.35 GB core and KV cache resident while fetching needed experts on-demand. Users can now run a 26-billion-parameter instruction-tuned model natively on entry-level Macs through a native app, CLI, or OpenAI-compatible server.

Read the full story

Apple Inference Optimization Model Optimization Gemma

Tencent Open-Sources AngelSpec: A Unified Training Framework for MTP and Block-Parallel Speculative Decoding on Hy3 Models

MarkTechPost 2 months ago 37

Tencent released AngelSpec, an open-source training framework for speculative-decoding draft models that uses different architectures optimized for different workloads rather than a single universal drafter. The framework includes MTP drafting for conversation (achieving 66.4% acceptance) and DFly block-diffusion drafting for code and math (reaching 4.79 mean accepted length on Hy3-A21B versus 3.69 for prior DFlash). This heterogeneity-aware approach delivers 1.98–2.40× speedup over standard autoregressive decoding across various concurrency levels.

Read the full story

Open Source Models Model Optimization

Every AI story that matters,
in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.