YA

Yash21 OpenMistral MoE

YashGGUF by RichardErkhovUpdated 2024-08-31
Download on Hugging Face
Parameters24B
Context32K
Layers32
Architecturellama
Smallest quant2.1 GB
Quick answer

Yash21 OpenMistral MoE needs about 16.2 GB of memory at Q4_K_M (a 14.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 2.1 GB (IQ3_M) to 25.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Yash21 OpenMistral MoE is a 24B-parameter Yash model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 2.1 GB (IQ3_M) to 25.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M2.1 GB 3.7 GB
Fits Get file →
Q2_K8.8 GB 10.4 GB
Too big Get file →
IQ3_XS9.9 GB 11.5 GB
Too big Get file →
Q3_K_S10.4 GB 12.0 GB
Too big Get file →
IQ3_S10.5 GB 12.0 GB
Too big Get file →
Q3_K11.6 GB 13.2 GB
Too big Get file →
Q3_K_M11.6 GB 13.2 GB
Too big Get file →
Q4_K_S11.8 GB 13.4 GB
Too big Get file →
Q3_K_L12.5 GB 14.1 GB
Too big Get file →
IQ4_XS13.0 GB 14.6 GB
Too big Get file →
Q4_013.6 GB 15.2 GB
Too big Get file →
IQ4_NL13.8 GB 15.3 GB
Too big Get file →
Q4_K14.6 GB 16.2 GB
Too big Get file →
Q4_K_M14.6 GB 16.2 GB
Too big Get file →
Q4_115.1 GB 16.7 GB
Too big Get file →
Q5_016.6 GB 18.2 GB
Too big Get file →
Q5_K_S16.6 GB 18.2 GB
Too big Get file →
Q5_K17.1 GB 18.7 GB
Too big Get file →
Q5_K_M17.1 GB 18.7 GB
Too big Get file →
Q5_118.1 GB 19.7 GB
Too big Get file →
Q6_K19.8 GB 21.4 GB
Too big Get file →
Q8_025.7 GB 27.2 GB
Too big Get file →

What GPU do you need for Yash21 OpenMistral MoE?

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: the best quant that fits is IQ3_M (2.1 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_M (2.1 GB file, about 3.7 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_M (2.1 GB file, about 3.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_S (10.5 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ4_NL (13.8 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.8 GB file, about 21.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.7 GB file, about 27.2 GB in use).

Which Yash21 OpenMistral MoE quant should you choose?

Q4_K_M is the usual starting point for Yash21 OpenMistral MoE: it balances file size and quality well. Here it is a 14.6 GB file.

The Q8_0 file is 25.7 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 IQ3_M at 2.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters24B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyYash
Downloads (HF)18
Last updated2024-08-31

Frequently asked questions about Yash21 OpenMistral MoE

How much VRAM does Yash21 OpenMistral MoE need?

About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.6 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 Yash21 OpenMistral MoE on an 8 GB GPU?

Yes, with IQ3_M: the 2.1 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Yash21 OpenMistral MoE GGUF?

It depends on the quant: IQ3_M is 2.1 GB, Q2_K is 8.8 GB, IQ3_XS is 9.9 GB, Q3_K_S is 10.4 GB, IQ3_S is 10.5 GB, Q3_K is 11.6 GB and 16 more.

What context length does Yash21 OpenMistral MoE support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Yash21 OpenMistral MoE GGUF?

The files are on Hugging Face in the RichardErkhov/Yash21_-_OpenMistral-MoE-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Yash models

All Yash →

Other medium models

All medium models →