YO

Yousei-22B

YouseiGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters21.8B
Context4K
Layers40
Architecturellama
Smallest quant5.2 GB
Quick answer

Yousei-22B needs about 22.4 GB of memory at Q4_K_M (a 13.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 quants, from 5.2 GB (IQ1_M) to 17.9 GB (Q6_K).

Yousei-22B – a 21.8B parameter Llama model with diverse merged DNA

Yousei-22B is a 21.8B parameter Llama model built from a merge of MythoMax13B, Enterredaas33B, Dendrite-II, Bacchus, and llama2-22b. It supports up to 4098 context tokens and is available in multiple GGUF quantizations.

Good at

  • Instructed writing
  • Roleplay with chat style
  • Handling complex prompts

Limits

  • No vision support
  • Potential refusals on mature content
  • License not specified

Best for

  • Chatbots needing detailed instructions
  • Creative writing assistants
  • Roleplay scenarios

Who it’s for. Developers and researchers who need a large Llama-based model with merged capabilities. Suitable for local deployment via llama.cpp using GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M5.2 GB 10.1 GB
Too big Get file →
IQ2_XXS5.9 GB 10.8 GB
Too big Get file →
IQ2_XS6.5 GB 11.4 GB
Too big Get file →
IQ2_S7.0 GB 11.9 GB
Too big Get file →
IQ2_M7.5 GB 12.4 GB
Too big Get file →
Q2_K8.1 GB 13.0 GB
Too big Get file →
IQ3_XXS8.3 GB 13.2 GB
Too big Get file →
IQ3_XS9.0 GB 13.8 GB
Too big Get file →
IQ3_S9.5 GB 14.3 GB
Too big Get file →
Q3_K_S9.5 GB 14.3 GB
Too big Get file →
IQ3_M10.0 GB 14.9 GB
Too big Get file →
Q3_K_M10.6 GB 15.5 GB
Too big Get file →
Q3_K_L11.6 GB 16.5 GB
Too big Get file →
IQ4_XS11.7 GB 16.5 GB
Too big Get file →
Q4_012.4 GB 17.2 GB
Too big Get file →
Q4_K_S12.4 GB 17.3 GB
Too big Get file →
Q4_K_M13.2 GB 18.0 GB
Too big Get file →
Q5_K_S15.0 GB 19.9 GB
Too big Get file →
Q5_K_M15.5 GB 20.3 GB
Too big Get file →
Q6_K17.9 GB 22.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (5.23 GB) or IQ2_XXS (5.9 GB). For 12 GB VRAM, Q4_0 (12.37 GB) or Q4_K_S (12.43 GB) are appropriate. Larger VRAM allows higher‑quality quants like Q5_K_M (15.47 GB).

What GPU do you need for Yousei-22B?

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: the best quant that fits is IQ2_XS (6.5 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (13.2 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (17.9 GB file, about 27.1 GB in use).

Which Yousei-22B quant should you choose?

Q4_K_M is the usual starting point for Yousei-22B: it balances file size and quality well. Here it is a 13.2 GB file.

If memory is tight, the smallest file is IQ1_M at 5.2 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
Parameters21.8B
Layers40
Trained context4,098 tokens
KV cache (fp16)1040 KB per token

Source

Quantized bymradermacher
FamilyYousei
Downloads (HF)2,331
Last updated2024-08-02

Frequently asked questions about Yousei-22B

How much VRAM does Yousei-22B need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 13.2 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 Yousei-22B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Yousei-22B GGUF?

It depends on the quant: IQ1_M is 5.2 GB, IQ2_XXS is 5.9 GB, IQ2_XS is 6.5 GB, IQ2_S is 7.0 GB, IQ2_M is 7.5 GB, Q2_K is 8.1 GB and 14 more.

What context length does Yousei-22B support?

The GGUF header lists a trained context length of 4,098 tokens (4K). The KV cache grows with the context you use: about 8.7 GB at 8K and 4.4 GB at 4K.

Where can I download Yousei-22B GGUF?

The files are on Hugging Face in the mradermacher/Yousei-22B-i1-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 Yousei-22B on 8 GB VRAM?

Yes, use IQ1_M or IQ2_XXS quantizations, which fit within 8 GB VRAM with approximate memory usage of 14.5–15.1 GB at 8k context.

Does Yousei-22B support vision?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports up to 4098 context tokens.

Other GGUFs of Yousei-22B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Yousei models

All Yousei →

Other medium models

All medium models →