Text model · Yi
YiYi 1.5 34B requirements
Yi family · 34B params · released May 2024. Minimum to run at Q4_K_M: Nvidia GeForce RTX 4090 (24GB).
LicenseApache-2.0· Commercial OK↓ 14.9K/mo♥ 278on HuggingFace
Q4_K_M
19.24 GB
Q8_0
34.03 GB
Total @ Q4 (4k)
~21.4 GB
Context
32 k
Quantization sizes
GGUF quantson disk
| Quantization | Size on disk |
|---|---|
| Q2_K | 14.2 GB est |
| Q3_K_M | 16.6 GB est |
| Q4_K_M (default) | 19.24 GB |
| Q5_K_M | 24.2 GB est |
| Q6_K | 27.9 GB est |
| Q8_0 | 34.03 GB |
| FP16 | 68 GB est |
Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.
Run it
llama.cpp
$
llama-cli -hf bartowski/Yi-1.5-34B-Chat-GGUF:Q4_K_M LM Studio
$
lms get bartowski/Yi-1.5-34B-Chat-GGUF Which devices can run Yi 1.5 34B?
Apple Silicon Macs
RAM-only laptops
iPhone & iPad
Android
NVIDIA GPUs
FAQ
How much VRAM or RAM does Yi 1.5 34B need?
At Q4_K_M, Yi 1.5 34B needs about 21.4 GB (weights ~19.24 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~36.2 GB.
Can Yi 1.5 34B run on a laptop?
Yi 1.5 34B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.
Can I use Yi 1.5 34B commercially?
Yes. Yi 1.5 34B is licensed Apache-2.0, which permits commercial use.
Yi 1.5 34B from 01.AI. Q4_K_M and Q8_0 sizes from the bartowski GGUF repo.
Sources
Memory figures are estimates. See methodology.