MI

MixtureofMerges-MoE-4x7b-v10-mixtralv0.3

MistralGGUF by jsfs11Updated 2024-05-28
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant14.6 GB
Quick answer

MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 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. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 is a 24.2B-parameter Mistral model in GGUF format, quantized by jsfs11. Its trained context length is 32K tokens. The repository has 1 quant file, from 14.6 GB (Q4_K_M) to 14.6 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M14.6 GB 16.2 GB
Too big Get file →

What GPU do you need for MixtureofMerges-MoE-4x7b-v10-mixtralv0.3?

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 Q4_K_M (14.6 GB file, about 16.2 GB in use).

Which MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 quant should you choose?

Q4_K_M is the usual starting point for MixtureofMerges-MoE-4x7b-v10-mixtralv0.3: it balances file size and quality well. Here it is a 14.6 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byjsfs11
FamilyMistral
Licenseapache-2.0
Downloads (HF)11
Last updated2024-05-28

Frequently asked questions about MixtureofMerges-MoE-4x7b-v10-mixtralv0.3

How much VRAM does MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 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 MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 GGUF?

It depends on the quant: Q4_K_M is 14.6 GB.

What context length does MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 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 MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 GGUF?

The files are on Hugging Face in the jsfs11/MixtureofMerges-MoE-4x7b-v10-mixtralv0.3-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 MixtureofMerges-MoE-4x7b-v10-mixtralv0.3 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.

Other GGUFs of NeuralSynthesis-7B-v0.1

Similar models

Browse all →

More from jsfs11

All by jsfs11 →

More Mistral models

All Mistral →

Other medium models

All medium models →