YI

mlinmg_sg-raccoon-yi-200k-2.0

YiGGUF by TheBlokeUpdated 2023-12-08
Download on Hugging Face
Parameters55.6B
Context195K
Layers98
Architecturellama
Smallest quant23.4 GB
Quick answer

mlinmg_sg-raccoon-yi-200k-2.0 needs about 37.1 GB of memory at Q4_K_M (a 33.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 23.4 GB (Q2_K) to 45.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 13.2 GB.

SG Raccoon Yi 55B 200K 2.0 – a 55.6B parameter Yi model with 200K context

SG Raccoon Yi 55B 200K 2.0 is a 55.6B parameter language model built on the Yi architecture. It merges two finetuned Yi 34B models and supports a 200,000 token context window. The model is available in multiple GGUF quantisations.

Good at

  • Large context handling
  • High parameter count
  • Yi architecture strengths

Limits

  • No vision support
  • License type "other"
  • Requires significant VRAM for higher quants

Best for

  • Long‑form content generation
  • Complex reasoning tasks
  • Custom prompt engineering

Who it’s for. Developers and researchers needing a large‑scale, long‑context language model for local deployment. Suitable for users with access to GPUs capable of handling 55B parameters in GGUF format.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K23.4 GB 27.2 GB
Too big Get file →
Q3_K_S24.1 GB 27.9 GB
Too big Get file →
Q3_K_M26.8 GB 30.6 GB
Too big Get file →
Q3_K_L29.3 GB 33.1 GB
Too big Get file →
Q4_031.4 GB 35.2 GB
Too big Get file →
Q4_K_S31.5 GB 35.3 GB
Too big Get file →
Q4_K_M33.3 GB 37.1 GB
Too big Get file →
Q5_038.3 GB 42.1 GB
Too big Get file →
Q5_K_S38.3 GB 42.1 GB
Too big Get file →
Q5_K_M39.3 GB 43.1 GB
Too big Get file →
Q6_K45.6 GB 49.4 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (23.44 GB file, ~27.2 GB VRAM at 8K context). For 16‑GB VRAM, Q3_K_S (24.07 GB file, ~27.9 GB VRAM) or Q3_K_M (26.78 GB file, ~30.6 GB VRAM). For 24‑GB VRAM, Q4_K_M (33.34 GB file, ~37.1 GB VRAM) offers a balance of quality and memory. Higher quants require more VRAM.

What GPU do you need for mlinmg_sg-raccoon-yi-200k-2.0?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q3_K_M (26.8 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (39.3 GB file, about 43.1 GB in use).

Which mlinmg_sg-raccoon-yi-200k-2.0 quant should you choose?

Q4_K_M is the usual starting point for mlinmg_sg-raccoon-yi-200k-2.0: it balances file size and quality well. Here it is a 33.3 GB file.

If memory is tight, the smallest file is Q2_K at 23.4 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
Parameters55.6B
Layers98
Trained context200,000 tokens
KV cache (fp16)392 KB per token

Source

Quantized byTheBloke
FamilyYi
Licenseother
Downloads (HF)2,189
Last updated2023-12-08

Frequently asked questions about mlinmg_sg-raccoon-yi-200k-2.0

How much VRAM does mlinmg_sg-raccoon-yi-200k-2.0 need?

About 37.1 GB at Q4_K_M with an 8K context window. That is the 33.3 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 mlinmg_sg-raccoon-yi-200k-2.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mlinmg_sg-raccoon-yi-200k-2.0 GGUF?

It depends on the quant: Q2_K is 23.4 GB, Q3_K_S is 24.1 GB, Q3_K_M is 26.8 GB, Q3_K_L is 29.3 GB, Q4_0 is 31.4 GB, Q4_K_S is 31.5 GB and 5 more.

What context length does mlinmg_sg-raccoon-yi-200k-2.0 support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 3.3 GB at 8K and 13.2 GB at 32K.

Where can I download mlinmg_sg-raccoon-yi-200k-2.0 GGUF?

The files are on Hugging Face in the TheBloke/SG-Raccoon-Yi-200k-2.0-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 mlinmg_sg-raccoon-yi-200k-2.0 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 SG Raccoon Yi 55B 200K 2.0 on 8 GB VRAM?

Use the Q2_K quant, which requires about 27.2 GB VRAM at 8K context. 8 GB VRAM is insufficient for any quant of this model.

What is the maximum context length supported?

The model was trained with 200,000 tokens and supports that full context length.

Does this model support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Yi models

All Yi →

Other large models

All large models →