MI

MixtureofMerges-MoE-4x7bRP-v11

MixtureofmergesGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant5.0 GB
Quick answer

MixtureofMerges-MoE-4x7bRP-v11 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 21 quants, from 5.0 GB (IQ1_S) to 19.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

24.2B Mixture of Experts model with vision and roleplay abilities

MixtureofMerges-MoE-4x7bRP-v11 is a 24.2B parameter llama architecture model. It is a Mixture of Experts built from four 7B models and supports vision and roleplay. The model was trained on 32768 context tokens and released under the apache-2.0 license.

Good at

  • Vision tasks
  • Roleplay interactions
  • Large context handling

Limits

  • No vision support on all quant types
  • Large memory requirement for high‑quality quants
  • Requires 8k context for estimates

Best for

  • Image captioning
  • Creative dialogue
  • Long‑form content generation

Who it’s for. Developers and researchers needing a large‑scale, vision‑capable LLM with MoE architecture. The model is suitable for applications that can handle the memory demands of higher‑quality quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S5.0 GB 6.6 GB
Fits Get file →
IQ1_M5.5 GB 7.1 GB
Fits Get file →
IQ2_XXS6.4 GB 8.0 GB
Tight Get file →
IQ2_XS7.1 GB 8.7 GB
Too big Get file →
IQ2_S7.3 GB 8.9 GB
Too big Get file →
IQ2_M8.0 GB 9.6 GB
Too big Get file →
Q2_K8.8 GB 10.4 GB
Too big Get file →
IQ3_XXS9.3 GB 10.9 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 →
IQ3_M10.7 GB 12.2 GB
Too big Get file →
Q3_K_M11.6 GB 13.2 GB
Too big Get file →
Q3_K_L12.5 GB 14.1 GB
Too big Get file →
IQ4_XS12.9 GB 14.5 GB
Too big Get file →
Q4_013.7 GB 15.3 GB
Too big Get file →
Q4_K_S13.7 GB 15.3 GB
Too big Get file →
Q4_K_M14.6 GB 16.2 GB
Too big Get file →
Q5_K_S16.6 GB 18.2 GB
Too big Get file →
Q5_K_M17.1 GB 18.7 GB
Too big Get file →
Q6_K19.8 GB 21.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (5.01 GB file, 6.6 GB memory) or IQ1_M (5.54 GB file, 7.1 GB memory). If 12 GB VRAM is available, IQ2_S (7.3 GB file, 8.9 GB memory) or Q2_K (8.85 GB file, 10.4 GB memory) are suitable. Higher‑quality quants such as Q5_K_M (17.14 GB file, 18.7 GB memory) require 20+ GB VRAM.

What GPU do you need for MixtureofMerges-MoE-4x7bRP-v11?

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: the best quant that fits is IQ2_XXS (6.4 GB file, about 8.0 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 Q4_K_S (13.7 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).

Which MixtureofMerges-MoE-4x7bRP-v11 quant should you choose?

Q4_K_M is the usual starting point for MixtureofMerges-MoE-4x7bRP-v11: it balances file size and quality well. Here it is a 14.6 GB file.

If memory is tight, the smallest file is IQ1_S at 5.0 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
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,170
Last updated2024-08-02

Frequently asked questions about MixtureofMerges-MoE-4x7bRP-v11

How much VRAM does MixtureofMerges-MoE-4x7bRP-v11 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-4x7bRP-v11 on an 8 GB GPU?

Yes, with IQ2_XXS: the 6.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MixtureofMerges-MoE-4x7bRP-v11 GGUF?

It depends on the quant: IQ1_S is 5.0 GB, IQ1_M is 5.5 GB, IQ2_XXS is 6.4 GB, IQ2_XS is 7.1 GB, IQ2_S is 7.3 GB, IQ2_M is 8.0 GB and 15 more.

What context length does MixtureofMerges-MoE-4x7bRP-v11 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-4x7bRP-v11 GGUF?

The files are on Hugging Face in the mradermacher/MixtureofMerges-MoE-4x7bRP-v11-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 MixtureofMerges-MoE-4x7bRP-v11 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.

Can I run this model on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM, with memory usage around 6.6 to 7.1 GB at 8k context.

Does the model support vision?

Yes, the model has vision capabilities as indicated in its detected abilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of MixtureofMerges-MoE-4x7bRP-v11

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mixtureofmerges models

All Mixtureofmerges →

Other medium models

All medium models →