YI

Yi-1.5-9B-32K

YiGGUF by RichardErkhovUpdated 2024-06-14
Download on Hugging Face
Parameters8.83B
Context32K
Layers48
Architecturellama
Smallest quant3.4 GB
Quick answer

Yi-1.5-9B-32K needs about 6.6 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 3.4 GB (Q2_K) to 9.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Yi‑1.5‑9B‑32K – 9‑billion‑parameter LLaMA‑style model with 32K context

Yi‑1.5‑9B‑32K is a 8.83‑billion‑parameter LLaMA‑based model. It supports a 32,768‑token context window and is trained on 500B tokens with 3M fine‑tuning samples. The model excels in coding, math, reasoning, and instruction following.

Good at

  • Coding and programming tasks
  • Mathematical reasoning
  • Instruction following

Limits

  • No vision support
  • License not specified
  • Requires large VRAM for higher quantizations

Best for

  • Local code generation
  • Math problem solving
  • Chatbot development

Who it’s for. Developers and researchers needing a large‑context language model for local inference. The model is suitable for applications that require detailed reasoning and code generation without external API calls.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.4 GB 4.7 GB
Fits Get file →
IQ3_XS3.7 GB 5.0 GB
Fits Get file →
Q3_K_S3.9 GB 5.2 GB
Fits Get file →
IQ3_S3.9 GB 5.2 GB
Fits Get file →
IQ3_M4.1 GB 5.4 GB
Fits Get file →
Q3_K4.3 GB 5.6 GB
Fits Get file →
Q3_K_M4.3 GB 5.6 GB
Fits Get file →
Q3_K_L4.7 GB 6.0 GB
Fits Get file →
IQ4_XS4.8 GB 6.1 GB
Fits Get file →
Q4_05.0 GB 6.3 GB
Fits Get file →
Q4_K_S5.1 GB 6.4 GB
Fits Get file →
IQ4_NL5.1 GB 6.4 GB
Fits Get file →
Q4_K5.3 GB 6.6 GB
Fits Get file →
Q4_K_M5.3 GB 6.6 GB
Fits Get file →
Q4_15.6 GB 6.9 GB
Fits Get file →
Q5_06.1 GB 7.4 GB
Tight Get file →
Q5_K_S6.1 GB 7.4 GB
Tight Get file →
Q5_K6.3 GB 7.6 GB
Tight Get file →
Q5_K_M6.3 GB 7.6 GB
Tight Get file →
Q5_16.6 GB 7.9 GB
Tight Get file →
Q6_K7.2 GB 8.6 GB
Too big Get file →
Q8_09.4 GB 10.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (5.04 GB file, ~6.3 GB memory) or Q4_K (5.33 GB file, ~6.6 GB memory). For 12 GB VRAM, Q5_0 (6.11 GB file, ~7.4 GB memory) or Q5_K (6.26 GB file, ~7.6 GB memory) are appropriate. Higher quantizations such as Q6_K or Q8_0 require more than 16 GB VRAM.

What GPU do you need for Yi-1.5-9B-32K?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_L (4.7 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (6.6 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.4 GB file, about 10.7 GB in use).

Which Yi-1.5-9B-32K quant should you choose?

Q4_K_M is the usual starting point for Yi-1.5-9B-32K: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 9.4 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.83B
Layers48
Trained context32,768 tokens
KV cache (fp16)96 KB per token

Source

Quantized byRichardErkhov
FamilyYi
Downloads (HF)878
Last updated2024-06-14

Frequently asked questions about Yi-1.5-9B-32K

How much VRAM does Yi-1.5-9B-32K need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Yi-1.5-9B-32K on an 8 GB GPU?

Yes, with Q5_1: the 6.6 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Yi-1.5-9B-32K GGUF?

It depends on the quant: Q2_K is 3.4 GB, IQ3_XS is 3.7 GB, Q3_K_S is 3.9 GB, IQ3_S is 3.9 GB, IQ3_M is 4.1 GB, Q3_K is 4.3 GB and 16 more.

What context length does Yi-1.5-9B-32K support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Yi-1.5-9B-32K GGUF?

The files are on Hugging Face in the RichardErkhov/01-ai_-_Yi-1.5-9B-32K-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Yi‑1.5‑9B‑32K on 8 GB VRAM?

Yes, using Q4_0 or Q4_K quantizations will fit within 8 GB VRAM with approximate memory usage of 6.3–6.6 GB.

Does the model support image input?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports a 32,768‑token context window.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Yi models

All Yi →

Other small models

All small models →