YI

Yi-1.5-34B-Chat

YiGGUF by bartowskiUpdated 2024-05-12
Download on Hugging Face
Parameters34.4B
Context4K
Layers60
Architecturellama
Smallest quant7.5 GB
Quick answer

Yi-1.5-34B-Chat needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 7.5 GB (IQ1_S) to 137.6 GB (F32).

Yi-1.5-34B-Chat, 34.4B parameter Llama‑style model

Yi-1.5-34B-Chat is a 34.4B parameter Llama‑based model released under the apache‑2.0 license. It supports a 4096 token context window and is available in multiple GGUF quantizations. The model is language agnostic and has no vision capabilities.

Good at

  • Large context handling
  • High token throughput
  • Versatile chat responses

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache‑2.0

Best for

  • Chatbot development
  • Content generation
  • Research prototyping

Who it’s for. Developers and researchers who need a large‑parameter LLM for text‑only workloads and can manage the memory requirements. The model is suitable for those who prefer open‑source licensing and want to experiment with different quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.5 GB 9.0 GB
Too big Get file →
IQ1_M8.2 GB 9.7 GB
Too big Get file →
IQ2_XXS9.3 GB 10.8 GB
Too big Get file →
IQ2_XS10.3 GB 11.8 GB
Too big Get file →
IQ2_S10.9 GB 12.4 GB
Too big Get file →
IQ2_M11.8 GB 13.3 GB
Too big Get file →
Q2_K12.8 GB 14.3 GB
Too big Get file →
IQ3_XXS13.3 GB 14.8 GB
Too big Get file →
IQ3_XS14.2 GB 15.7 GB
Too big Get file →
Q3_K_S15.0 GB 16.5 GB
Too big Get file →
IQ3_S15.0 GB 16.5 GB
Too big Get file →
IQ3_M15.6 GB 17.1 GB
Too big Get file →
Q3_K_M16.7 GB 18.2 GB
Too big Get file →
Q3_K_L18.1 GB 19.6 GB
Too big Get file →
IQ4_XS18.5 GB 20.0 GB
Too big Get file →
IQ4_NL19.5 GB 21.0 GB
Too big Get file →
Q4_K_S19.6 GB 21.1 GB
Too big Get file →
Q4_K_M20.7 GB 22.2 GB
Too big Get file →
Q5_K_S23.7 GB 25.2 GB
Too big Get file →
Q5_K_M24.3 GB 25.8 GB
Too big Get file →
Q6_K28.2 GB 29.7 GB
Too big Get file →
Q8_036.5 GB 38.0 GB
Too big Get file →
F32137.6 GB (5 parts) 139.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.5 GB file, 10 GB memory). For 16 GB VRAM, IQ2_M (11.79 GB file, 14.3 GB memory) or Q3_K_M (16.65 GB file, 19.2 GB memory). For 24 GB VRAM, Q4_K_M (20.66 GB file, 23.2 GB memory) or Q5_K_M (24.32 GB file, 26.8 GB memory).

What GPU do you need for Yi-1.5-34B-Chat?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (9.3 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (13.3 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).

Which Yi-1.5-34B-Chat quant should you choose?

Q4_K_M is the usual starting point for Yi-1.5-34B-Chat: it balances file size and quality well. Here it is a 20.7 GB file.

The Q8_0 file is 36.5 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 IQ1_S at 7.5 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
Parameters34.4B
Layers60
Trained context4,096 tokens
KV cache (fp16)240 KB per token

Source

Quantized bybartowski
FamilyYi
Licenseapache-2.0
Downloads (HF)573
Last updated2024-05-12

Frequently asked questions about Yi-1.5-34B-Chat

How much VRAM does Yi-1.5-34B-Chat need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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-1.5-34B-Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Yi-1.5-34B-Chat GGUF?

It depends on the quant: IQ1_S is 7.5 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.3 GB, IQ2_XS is 10.3 GB, IQ2_S is 10.9 GB, IQ2_M is 11.8 GB and 17 more.

What context length does Yi-1.5-34B-Chat support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.0 GB at 8K and 1.0 GB at 4K.

Where can I download Yi-1.5-34B-Chat GGUF?

The files are on Hugging Face in the bartowski/Yi-1.5-34B-Chat-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Yi-1.5-34B-Chat use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Yi-1.5-34B-Chat on 8 GB VRAM?

Use the IQ1_S quant, which is 7.5 GB and requires about 10 GB memory at 8k context.

What quant is best for 16 GB VRAM?

IQ2_M or Q3_K_M provide a good balance of size and memory usage for 16 GB VRAM.

Is there a quant that fits in 24 GB VRAM?

Q4_K_M or Q5_K_M fit within 24 GB VRAM, with file sizes 20.66 GB and 24.32 GB respectively.

Similar models

Browse all →

More from bartowski

All by bartowski →

More Yi models

All Yi →

Other large models

All large models →