Translation models that run on 16 GB
15 models with published weights that fit in 16 GB — the common laptop. Counted at four-bit quantisation, weights only, leaving the machine about a third of its memory and a gigabyte for context: room for roughly 16 billion parameters. A mixture of experts is counted in full, because it is held in full even though only a few experts compute.
The commonest laptop configuration, and the point where a genuinely useful model runs locally: fourteen billion parameters at four-bit fits with room to spare for the context. Expect a capable general assistant that will not match the frontier, and remember that anything else the machine is doing competes for the same memory.
Models and services aimed at moving text between languages. A general chat model will translate too, and often well; a dedicated one earns its place with glossaries, formality control, document formats it keeps intact, and rates that assume volume. Check which direction was measured — most quality figures are for translating into English, and the other direction is harder.
- translategemma-12b-itGoogle13.2B≈8.6 GB at 4-bit
- granite-speech-3.3-8bIBM Granite8.0B≈5.2 GB at 4-bit
- Hy-MT2-7BTencent Hunyuan7.0B≈4.5 GB at 4-bit1 also selling it hosted
- Seed-X-PPO-7BByteDance Seed7.0B≈4.5 GB at 4-bit
- translategemma-4b-itGoogle5.0B≈3.2 GB at 4-bit
- Voxtral-Mini-3B-2507Mistral AI3.0B≈2.0 GB at 4-bit2 also selling it hosted
- madlad400-3b-mtGoogle2.9B≈1.9 GB at 4-bit
- seamless-m4t-v2-largeAI at Meta2.3B≈1.5 GB at 4-bit
- Hy-MT2-1.8BTencent Hunyuan1.8B≈1.2 GB at 4-bit1 also selling it hosted
- Whisper Large v3OpenAI1.5B≈1.0 GB at 4-bit2 also selling it hosted
- whisper-largeOpenAI1.5B≈1.0 GB at 4-bit
- whisper-large-v2OpenAI1.5B≈1.0 GB at 4-bit
- canary-1b-v2NVIDIA1.0B≈0.6 GB at 4-bit
- whisper-smallOpenAI0.2B≈0.2 GB at 4-bit
- whisper-tinyOpenAI0.0B≈0.0 GB at 4-bit