Configure a rig →

Yi6B params33k context

Yi 1.5 6B locally

Yi 1.5 6B is an open-weight LLM from the Yi family with 6B parameters. Main use: chat, RAG and general assistance. Detected minimum hardware: GTX 1650 (4 GB).

Check on my GPU →Hugging Face ↗

Technical facts

Parameters6B

Max context33k

Q4_K_M3.8 GB

Q5_K_M4.6 GB

Q86.7 GB

FP1613.4 GB

FamilyYi

Last sync2026-05-12

Available quantizations

GGUF weights

Q4_K_M

3.8GB

Acceptable. Good compromise when VRAM is limited.

Q5_K_M

4.6GB

Good quality. Sweet spot for size and precision.

Q8

6.7GB

Near-FP16 quality. Comfortable for production.

FP16

13.4GB

Reference precision. Maximum quality, doubled VRAM.

Compatible GPUs

12 single-GPU

GPUs that can run Yi 1.5 6B on a single card, ranked by VRAM headroom.

3.8 / 4 GBtight · Q4

4.6 / 6 GBcomfortable · Q5

4.6 / 6 GBcomfortable · Q5

4.6 / 6 GBcomfortable · Q5

4.6 / 6 GBcomfortable · Q5

4.6 / 6 GBcomfortable · Q5

4.6 / 6 GBcomfortable · Q5

6 GB · Arc Alchemist

4.6 / 6 GBcomfortable · Q5

6.7 / 8 GBcomfortable · Q8

6.7 / 8 GBcomfortable · Q8

6.7 / 8 GBcomfortable · Q8

6.7 / 8 GBcomfortable · Q8

Recommended multi-GPU rigs

2x / 4x consumer GPUs

For Yi 1.5 6B at higher quantization or with more context, a multi-GPU rig gives more headroom.

6.7 / 8 GBcomfortable · Q8

2× GTX 1060 6GB

12 GB · GTX 10

6.7 / 12 GBcomfortable · Q8

12 GB · GTX 16

6.7 / 12 GBcomfortable · Q8

2× GTX 1660 Super

12 GB · GTX 16

6.7 / 12 GBcomfortable · Q8

2× GTX 1660 Ti

12 GB · GTX 16

6.7 / 12 GBcomfortable · Q8

2× RTX 2060 6GB

12 GB · RTX 20

6.7 / 12 GBcomfortable · Q8

2× RTX 3050 6GB

12 GB · RTX 30

6.7 / 12 GBcomfortable · Q8

12 GB · Arc Alchemist

6.7 / 12 GBcomfortable · Q8

Recommended rig

2× GTX 1650

Yi 1.5 6B with Ubuntu, vLLM, Open WebUI and the model already downloaded.

Similar models

Yi 1.5 9B9B

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