MI

MixtureofMerges MoE 2x7b v6 i1

MixtureofmergesGGUF by mradermacherUpdated 2024-11-28
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

MixtureofMerges MoE 2x7b v6 i1 needs about 9.4 GB of memory at Q4_K_M (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.7 GB (IQ1_S) to 10.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

MixtureofMerges MoE 2x7b v6 i1 – 12.9B parameter Llama‑style model

MixtureofMerges MoE 2x7b v6 i1 is a 12.9B parameter Llama‑based model with a mixture of experts architecture. It supports a 32768 token context window and is released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Mixture of experts inference
  • High token throughput

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache‑2.0

Best for

  • Long‑form content generation
  • Complex reasoning tasks
  • Fine‑tuning with limited VRAM

Who it’s for. Developers and researchers who need a large Llama‑style model with MoE capabilities and a flexible quantization set. The model is suitable for local deployment using llama.cpp or similar engines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.7 GB 4.3 GB
Fits Get file →
IQ1_M3.0 GB 4.6 GB
Fits Get file →
IQ2_XXS3.5 GB 5.0 GB
Fits Get file →
IQ2_XS3.8 GB 5.4 GB
Fits Get file →
IQ2_S4.0 GB 5.5 GB
Fits Get file →
IQ2_M4.3 GB 5.9 GB
Fits Get file →
Q2_K4.8 GB 6.3 GB
Fits Get file →
IQ3_XXS5.0 GB 6.6 GB
Fits Get file →
IQ3_XS5.3 GB 6.9 GB
Fits Get file →
Q3_K_S5.6 GB 7.2 GB
Fits Get file →
IQ3_S5.6 GB 7.2 GB
Fits Get file →
IQ3_M5.7 GB 7.3 GB
Tight Get file →
Q3_K_M6.2 GB 7.8 GB
Tight Get file →
Q3_K_L6.7 GB 8.3 GB
Too big Get file →
IQ4_XS6.9 GB 8.5 GB
Too big Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_K_S7.3 GB 8.9 GB
Too big Get file →
Q4_K_M7.8 GB 9.4 GB
Too big Get file →
Q5_K_S8.9 GB 10.4 GB
Too big Get file →
Q5_K_M9.1 GB 10.7 GB
Too big Get file →
Q6_K10.6 GB 12.1 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (file size 2.75 GB, estimated 4.3 GB memory). For 12‑GB VRAM, IQ2_M (4.33 GB, 5.9 GB memory) or Q3_K_M (6.21 GB, 7.8 GB memory) are good choices. For 16‑GB VRAM, Q4_K_M (7.78 GB, 9.4 GB memory) or Q5_K_M (9.13 GB, 10.7 GB memory) provide higher quality.

What GPU do you need for MixtureofMerges MoE 2x7b v6 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: the best quant that fits is IQ2_M (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.2 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.1 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.6 GB file, about 12.1 GB in use).

Which MixtureofMerges MoE 2x7b v6 i1 quant should you choose?

Q4_K_M is the usual starting point for MixtureofMerges MoE 2x7b v6 i1: it balances file size and quality well. Here it is a 7.8 GB file.

If memory is tight, the smallest file is IQ1_S at 2.7 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
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)856
Last updated2024-11-28

Frequently asked questions about MixtureofMerges MoE 2x7b v6 i1

How much VRAM does MixtureofMerges MoE 2x7b v6 i1 need?

About 9.4 GB at Q4_K_M with an 8K context window. That is the 7.8 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 2x7b v6 i1 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.2 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MixtureofMerges MoE 2x7b v6 i1 GGUF?

It depends on the quant: IQ1_S is 2.7 GB, IQ1_M is 3.0 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.8 GB, IQ2_S is 4.0 GB, IQ2_M is 4.3 GB and 18 more.

What context length does MixtureofMerges MoE 2x7b v6 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 MixtureofMerges MoE 2x7b v6 i1 GGUF?

The files are on Hugging Face in the mradermacher/MixtureofMerges-MoE-2x7b-v6-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 2x7b v6 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?

Yes, the IQ1_S quantization requires about 4.3 GB of VRAM at 8k context, which fits within an 8 GB budget.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of MixtureofMerges-MoE-2x7b-v6

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mixtureofmerges models

All Mixtureofmerges →

Other medium models

All medium models →