TinyLlama1.1B params2k contextpopular

TinyLlama 1.1B locally

TinyLlama 1.1B is an open-weight LLM from the TinyLlama family with 1.1B parameters. Main use: chat, RAG and general assistance. Detected minimum hardware: GTX 1650 (4 GB).

Technical facts
Parameters1.1B
Max context2k
Q4_K_M0.7 GB
Q5_K_M0.8 GB
Q81.2 GB
FP162.5 GB
FamilyTinyLlama
Last sync2026-05-12

Available quantizations

Q4_K_M
0.7GB

Acceptable. Good compromise when VRAM is limited.

Q5_K_M
0.8GB

Good quality. Sweet spot for size and precision.

Q8
1.2GB

Near-FP16 quality. Comfortable for production.

FP16
2.5GB

Reference precision. Maximum quality, doubled VRAM.

Compatible GPUs

GPUs that can run TinyLlama 1.1B on a single card, ranked by VRAM headroom.

Recommended multi-GPU rigs

For TinyLlama 1.1B at higher quantization or with more context, a multi-GPU rig gives more headroom.

Recommended rig

2× GTX 1650

TinyLlama 1.1B with Ubuntu, vLLM, Open WebUI and the model already downloaded.

Configure

VRAM estimates: parameters x bits/8 plus margin. Real performance varies by engine, context length and batch size.
sync: 2026-05-12