ME

mera mix 4x7B i1

MeraGGUF by mradermacherUpdated 2024-05-05
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant5.0 GB
Quick answer

mera mix 4x7B i1 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 parameter MoE model with 32k context

mera mix 4x7B i1 is a mixture of experts model based on the Mera family. It contains 24.2B parameters and supports a 32768 token context window. The model is released under the apache-2.0 license.

Good at

  • Large context handling
  • Mixture of experts efficiency
  • OpenLLM Eval performance

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Large VRAM needed for higher quants

Best for

  • Long‑form text generation
  • Context‑heavy dialogue
  • Research prototyping

Who it’s for. Developers and researchers who need a high‑capacity LLM with a large context window and are comfortable managing MoE models. The model is suitable for applications that can benefit from the 32k token context and the MoE architecture.

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_M10.6 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 at 8k context). For 12‑GB VRAM, IQ2_S (7.3 GB file, 8.9 GB memory) or Q2_K (8.84 GB file, 10.4 GB memory). For 16‑GB VRAM, Q4_K_M (14.61 GB file, 16.2 GB memory) or Q5_K_S (16.63 GB file, 18.2 GB memory). Estimates are approximate.

What GPU do you need for mera mix 4x7B i1?

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 mera mix 4x7B i1 quant should you choose?

Q4_K_M is the usual starting point for mera mix 4x7B i1: 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
FamilyMera
Licenseapache-2.0
Downloads (HF)1,922
Last updated2024-05-05

Frequently asked questions about mera mix 4x7B i1

How much VRAM does mera mix 4x7B i1 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 mera mix 4x7B i1 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 mera mix 4x7B i1 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 mera mix 4x7B i1 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 mera mix 4x7B i1 GGUF?

The files are on Hugging Face in the mradermacher/mera-mix-4x7B-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 mera mix 4x7B i1 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?

Use the IQ1_S quant, which requires about 6.6 GB memory at 8k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of mera-mix-4x7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mera models

All Mera →

Other medium models

All medium models →