Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// Open-model VRAM table · family

NVIDIA Parakeet / Canary speech: local deployment & VRAM

10 open-weight models from NVIDIA (10 official repos incl. quantised builds).

Filter by my hardware → VRAM calculator

official orgs: nvidialatest 2026-04-07memory = estimate

01Speech-to-text (10)

ModelParamsBF164-bitSmallest GPU (4-bit)Mac (4-bit)LicenceReleased
parakeet-unified-en-0.6b600M 1.8 GB0.9 GB 8GB GPUMac 16GB Commercial with conditions2026-04-07
multitalker-parakeet-streaming-0.6b-v1 ↗600M 1.8 GB0.9 GB 8GB GPUMac 16GB Commercial with conditions2025-10-15
canary-1b-v2979M 2.7 GB1.2 GB 8GB GPUMac 16GB Commercial OK2025-08-04
canary-qwen-2.5b2.56B 6.1 GB2.2 GB 8GB GPUMac 16GB Commercial OK2025-06-26
parakeet-tdt-0.6b-v2600M 1.8 GB0.9 GB 8GB GPUMac 16GB Commercial OK2025-04-15
canary-180m-flash ↗180M 0.9 GB0.6 GB 8GB GPUMac 16GB Commercial OK2025-03-11
canary-1b-flash811M 2.3 GB1.0 GB 8GB GPUMac 16GB Commercial OK2025-03-07
parakeet-tdt_ctc-110m110M 0.7 GB0.6 GB 8GB GPUMac 16GB Commercial OK2024-09-17
parakeet-tdt_ctc-0.6b-ja600M 1.8 GB0.9 GB 8GB GPUMac 16GB Commercial OK2024-05-13
parakeet-tdt_ctc-1.1b ↗1.1B 2.9 GB1.2 GB 8GB GPUMac 16GB Commercial OK2024-05-07

02Other families

Qwen · IBM Granite · NVIDIA Nemotron · Gemma · Mistral / Magistral / Devstral · GLM / CogVideoX (Z.ai) · DeepSeek · Ai2 OLMo / Molmo · Ant Ling / Ring / Ming · Liquid LFM · MiniCPM / VoxCPM · Tencent Hunyuan / Hy · Phi · Llama · Meituan LongCat · Jina embeddings & rerankers · Wan · Kimi · Cohere Command / Aya · Xiaomi MiMo · FLUX · Microsoft VibeVoice / Fara / Harrier · InternLM / Intern-S · StepFun Step · MiniMax · Baidu ERNIE · Stable Diffusion / Stable Audio · Yi (01.AI) · ByteDance Seed · SmolLM / SmolVLM · BGE embeddings & rerankers · LTX Video · FunAudioLLM speech · gpt-oss · poolside Laguna · Whisper · Baichuan · Thinking Machines Inkling · xAI Grok · rednote dots

Totals include 10% + 0.5GB overhead and one 8K-token KV cache for text models. Estimates only. Method →

Data updated: Self-host open models(UTC+8)