Quantization
Curated collection of thoughts and builds centered around Quantization.
Daily Briefings 38
- Kinference Control Plane cuts TTFT 95%; Ripple-65B achieves top open-source coding benchmark
- Together AI's Agent-Driven Compiler Boosts Inference 2.6x; Box Deploys Nemotron for Token-Efficient RAG
- Anthropic's Message Threads cut TTFT by 35% for long conversations; Zyphra releases hierarchical attention for subquadratic scaling
- DeepSeek and Nace AI Release Open-Weight Agent and Decision Models; OpenAI Shifts to Token-Based Pricing
- GLM 5.3 Autonomously Built Firefox Exploits; Mistral Releases Trillion-Parameter Model Weights
- Nvidia releases open-weight speech model for 40 languages; IBM's Granite Switch enables model updates without retraining
- FlashMap Achieves 6.14x LLM Decoding Speedup; Liquid AI Releases 2B Multimodal Models
- Opera Launches WebAI Standard for Browser-Based Local Inference; Mirendil Releases Fern 0.1 with 10M-Token Context
- Tsinghua's AKV cuts LLM agent inference costs 27.7%; TokenGate accelerates long-context prefill 11.3x
- Nvidia open-sources Flora for robot video labeling at 1/125th GPT-6 Astra cost; Microsoft releases decentralized agent orchestration framework
- Meta's Muse Spark Open; NVIDIA Nemotron 3.5 Super VL; Black Forest Labs FLUX 3 Image Klein
- Liquid AI releases 2B-active MoE for on-device agents; Google ships Gemini 4 Argon with 1M token output
- Microsoft scales Maia chips to gigawatt inference; agent context-clearing boosts solution quality
- Aleph Alpha releases Kolibri open-weight MoE; Google tightens federated learning privacy
- Aleph Alpha releases Kolibri open-weight MoE; Google tightens Gemini access
- Nvidia embeds agent containment in hardware; Fireworks AI cuts token usage 40% with post-trained Kimi K3
- Meta's Muse offers cloud Ubuntu environment to 500K users; Black Forest Labs releases FLUX 3 Action robotics model
- Contrastive-LM releases CLM-8B agent scoring model; Google ships Gemini 3.8 Flash TTS
- Hugging Face integrates llama.cpp quantization; Xiaomi's MiMo-V2.6-Pro tops open model rankings
- StepFun releases Step 5 Preview 600B MoE model; Alibaba open-sources Qwen-Image-2.1 with 7B parameters
- AI infrastructure strain as data center power demand surges; token costs fall 41% as enterprises shift models
- Reducto ships r-1 document parser at 1¢/page; OpenBMB releases MiniCPM5-2B small language model
- IFM releases K2 Horizon fleet of six open-weight models (0.9B–375B); Meta FAIR introduces research preference models to rank GPU experiments
- OpenAI's Jalapeño inference chip outperforms Nvidia on throughput and efficiency; IBM releases Granite 4.2 open-weight models
- FreeToken runs 753B MoE models on single GPU; agentic token consumption surges 14x
- OpenAI patches Codex file-deletion bug; Anthropic demonstrates agent-driven protein design
- Meta releases Muse Glimmer 30B agentic model; webAI open-sources formal-logic models for local inference
- AMD Acquires Taalas for On-Chip Model Weights; Agent Plugin Standard Reaches 1.0
- Liquid AI Releases On-Device Agentic Model; Microsoft Open-Sources Unit-Test Agent
- Meta launches Muse Code agent for large codebases; Mistral's 3B Shieldstral matches larger safety models
- Alibaba Qwen3.8-Max reaches general availability; Thinking Machines releases 12B active MoE model
- DeepSeek V4 Flash Update Matches GPT-5.6 Luna at 60% Lower Cost; Thinking Machines Releases Smaller Inkling Model
- Liquid AI releases 8K-context encoders optimized for CPU inference; Fireworks launches routing layer for open-weight coding models
- Cursor's Agent Swarm Achieves 100% SQLite Rebuild; Black Forest Labs Releases FLUX 3 Multimodal Model
- OpenAI models breach Hugging Face during internal security test; Google releases three new Gemini Flash variants
- Feyn Labs ships SQRL text-to-SQL family; Moonshot maxes GPU capacity on Kimi K3 in 48 hours
- Thinking Machines releases Inkling open model; PrismML compresses 27B reasoning model to iPhone
- PrismML ships 1-bit and ternary Qwen3.6-27B builds; Mistral's Robostral Navigate runs on one RGB camera