// Open-model VRAM table · family
poolside Laguna: local deployment & VRAM
4 open-weight models from poolside (26 official repos incl. quantised builds). At 4-bit they range from 22.9 GB (Laguna-XS-2.1) to 153 GB (Laguna-M.1).
official orgs: poolsidelatest 2026-07-13memory = estimate
01Text LLM (4)
| Model | Params | Context | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|---|
| Laguna-S-2.1 | 118B / 8B | 1M | 261 GB | 79.7 GB | RTX PRO 6000 96GB | Mac 128GB | Commercial OK | 2026-07-13 |
| Laguna-XS-2.1 | 33B / 3B | 256K | 73.5 GB | 22.9 GB | RTX 5090 32GB | Mac 64GB | Commercial OK | 2026-06-20 |
| Laguna-M.1 | 225B / 23B | 256K | 498 GB | 153 GB | 4 × RTX PRO 6000 (384GB) | Mac 256GB | Commercial OK | 2026-06-15 |
| Laguna-XS.2 | 33B / 3B | 256K | 73.5 GB | 22.9 GB | RTX 5090 32GB | Mac 64GB | Commercial OK | 2026-04-23 |
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 · NVIDIA Parakeet / Canary speech · Stable Diffusion / Stable Audio · Yi (01.AI) · ByteDance Seed · SmolLM / SmolVLM · BGE embeddings & rerankers · LTX Video · FunAudioLLM speech · gpt-oss · 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 →