YI

Yi 70B 200k RPMerge Franken

YiGGUF by mradermacherUpdated 2024-12-02
Download on Hugging Face
Parameters71.2B
Context195K
Layers126
Architecturellama
Smallest quant15.2 GB
Quick answer

Yi 70B 200k RPMerge Franken needs about 47.4 GB of memory at Q4_K_M (a 42.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 19 quants, from 15.2 GB (IQ1_S) to 49.0 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 16.9 GB.

Yi 70B 200k RPMerge Franken – a 71B llama model with 200k context

Yi 70B 200k RPMerge Franken is a 71.2B parameter llama model. It was created by interleaving layers of Yi‑34B‑200K‑RPMerge. The model supports a 200000 token context window and is available in multiple GGUF quantizations.

Good at

  • Large context reasoning
  • High parameter count performance
  • Custom quant options

Limits

  • No vision support
  • License is other
  • No mixture of experts

Best for

  • Long‑form content generation
  • Complex reasoning tasks
  • Custom quant deployment

Who it’s for. Developers and researchers who need a large‑parameter llama model with extended context. The model is suitable for users who can manage the memory requirements of the various quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S15.2 GB 20.0 GB
Too big Get file →
IQ1_M16.7 GB 21.4 GB
Too big Get file →
IQ2_XXS19.0 GB 23.8 GB
Too big Get file →
IQ2_XS21.1 GB 25.9 GB
Too big Get file →
IQ2_S22.3 GB 27.0 GB
Too big Get file →
IQ2_M24.2 GB 28.9 GB
Too big Get file →
Q2_K26.4 GB 31.1 GB
Too big Get file →
IQ3_XXS27.4 GB 32.2 GB
Too big Get file →
IQ3_XS29.3 GB 34.0 GB
Too big Get file →
Q3_K_S30.8 GB 35.5 GB
Too big Get file →
IQ3_S30.9 GB 35.6 GB
Too big Get file →
IQ3_M32.1 GB 36.8 GB
Too big Get file →
Q3_K_M34.4 GB 39.1 GB
Too big Get file →
Q3_K_L37.5 GB 42.2 GB
Too big Get file →
IQ4_XS38.1 GB 42.8 GB
Too big Get file →
Q4_040.3 GB 45.0 GB
Too big Get file →
Q4_K_S40.5 GB 45.2 GB
Too big Get file →
Q4_K_M42.6 GB 47.4 GB
Too big Get file →
Q5_K_S49.0 GB 53.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (15.24 GB file, ~20 GB memory at 8k context). For 12 GB VRAM, IQ1_M (16.66 GB file, ~21.4 GB memory). For 16 GB VRAM, IQ2_S (22.31 GB file, ~27 GB memory).

What GPU do you need for Yi 70B 200k RPMerge Franken?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is IQ2_XXS (19.0 GB file, about 23.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 31.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.6 GB file, about 47.4 GB in use).

Which Yi 70B 200k RPMerge Franken quant should you choose?

Q4_K_M is the usual starting point for Yi 70B 200k RPMerge Franken: it balances file size and quality well. Here it is a 42.6 GB file.

If memory is tight, the smallest file is IQ1_S at 15.2 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
Parameters71.2B
Layers126
Trained context200,000 tokens
KV cache (fp16)504 KB per token

Source

Quantized bymradermacher
FamilyYi
Licenseother
Downloads (HF)1,291
Last updated2024-12-02

Frequently asked questions about Yi 70B 200k RPMerge Franken

How much VRAM does Yi 70B 200k RPMerge Franken need?

About 47.4 GB at Q4_K_M with an 8K context window. That is the 42.6 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 70B 200k RPMerge Franken on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Yi 70B 200k RPMerge Franken GGUF?

It depends on the quant: IQ1_S is 15.2 GB, IQ1_M is 16.7 GB, IQ2_XXS is 19.0 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.3 GB, IQ2_M is 24.2 GB and 13 more.

What context length does Yi 70B 200k RPMerge Franken support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.9 GB at 32K.

Where can I download Yi 70B 200k RPMerge Franken GGUF?

The files are on Hugging Face in the mradermacher/Yi-70B-200k-RPMerge-Franken-i1-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 70B 200k RPMerge Franken use?

Hugging Face lists the license as other. 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 this model on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 20 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The license is listed as other; check the repository for details.

Other GGUFs of Yi-70B-200k-RPMerge-Franken

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Yi models

All Yi →

Other large models

All large models →