// Open-model VRAM table · family
SmolLM / SmolVLM: local deployment & VRAM
8 open-weight models from Hugging Face (27 official repos incl. quantised builds). At 4-bit they range from 0.8 GB (SmolLM2-135M) to 3.3 GB (SmolLM2-1.7B).
official orgs: HuggingFaceTBlatest 2025-07-08memory = estimate
01Text LLM (7)
| Model | Params | Context | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|---|
| SmolLM3-3B | 3.08B | 64K | 7.9 GB | 3.2 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-07-08 |
| SmolLM2-135M | 135M | 8K | 1.0 GB | 0.8 GB | 8GB GPU | Mac 16GB | Commercial OK | 2024-10-31 |
| SmolLM2-360M | 362M | 8K | 1.6 GB | 1.1 GB | 8GB GPU | Mac 16GB | Commercial OK | 2024-10-31 |
| SmolLM2-1.7B | 1.71B | 8K | 5.9 GB | 3.3 GB | 8GB GPU | Mac 16GB | Commercial OK | 2024-10-30 |
| SmolLM-135M | 135M | 2K | 1.0 GB | 0.8 GB | 8GB GPU | Mac 16GB | Commercial OK | 2024-07-14 |
| SmolLM-360M | 362M | 2K | 1.6 GB | 1.1 GB | 8GB GPU | Mac 16GB | Commercial OK | 2024-07-14 |
| SmolLM-1.7B | 1.71B | 2K | 5.9 GB | 3.3 GB | 8GB GPU | Mac 16GB | Commercial OK | 2024-07-14 |
02Vision-language (1)
| Model | Params | Context | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|---|
| SmolVLM2-2.2B-Instruct | 2.25B | 8K | 5.4 GB | 2.0 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-02-08 |
03Other 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 · 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 →