// Yi (01.AI) · Text LLM
Yi-1.5-9B-Chat: VRAM & local deployment
8.83B parameters. About 7.2 GB at 4-bit and 20.7 GB at BF16 with one 8K-token request.
released 2024-05-10licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | 01.AI · 01-ai |
|---|---|
| Family / series | Yi (01.AI) · Yi-1.5 |
| Type | Text LLM (text-generation) |
| Parameters | 8.83B Source: counted from official safetensors weights |
| Context length | 4K tokens (4,096)max_position_embeddings in config.json |
| Architecture | 48 layers · GQA |
| Released weights | BF16 · 17.7 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2024-05-10 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Smallest GPU | Mac |
|---|---|---|---|---|
| BF16 / FP16 (original) | 17.7 GB | 20.7 GB | RTX 4090 24GB | Mac 36GB |
| FP8 / INT8 / Q8_0 | 9.4 GB | 11.6 GB | 16GB GPU | Mac 24GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 5.3 GB | 7.2 GB | 8GB GPU | Mac 16GB |
KV cache per request: 8K 0.8 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- Transformers — library declared on Hugging Face
04Official repositories & quantised builds
2 official repo(s) from 01-ai.
- Yi-1.5-9B-Chat Instruct
- Yi-1.5-9B main
05Other Yi (01.AI) models
All 9 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Yi-1.5-6B · same series | 6.06B | 5.1 GB | 2024-05-11 |
| Yi-1.5-34B-Chat · same series | 34.4B | 25.4 GB | 2024-05-10 |
| Yi-Coder-1.5B-Chat | 1.48B | 3.1 GB | 2024-08-21 |
| Yi-Coder-9B-Chat | 8.83B | 7.2 GB | 2024-08-21 |
| Yi-1.5-9B-Chat-16K | 8.83B | 7.2 GB | 2024-05-15 |
| Yi-1.5-34B-Chat-16K | 34.4B | 25.4 GB | 2024-05-15 |
| Yi-1.5-9B-32K | 8.83B | 7.2 GB | 2024-05-15 |
| Yi-1.5-34B-32K | 34.4B | 25.4 GB | 2024-05-15 |
06Sources
Data checked 2024-06-26. Parameters, context and licence are copied from the official repository; memory figures are our estimates.