NA

NaruMOE-3x7B-v2

NarumoeGGUF by mradermacherUpdated 2024-06-03
Download on Hugging Face
Parameters18.5B
Context32K
Layers32
Architecturellama
Smallest quant6.8 GB
Quick answer

NaruMOE-3x7B-v2 needs about 12.8 GB of memory at Q4_K_M (a 11.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 6.8 GB (Q2_K) to 19.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

18.5B‑parameter NaruMOE model with 32k context

NaruMOE-3x7B-v2 is a 18.5 billion‑parameter mixture‑of‑experts model based on the llama architecture. It supports a 32768‑token context window and is released under a CC‑BY‑NC‑4.0 license.

Good at

  • Roleplay
  • Large context handling
  • Mixture‑of‑experts inference

Limits

  • No vision support
  • CC‑BY‑NC‑4.0 license restricts commercial use
  • Large VRAM requirement for higher quants

Best for

  • Interactive storytelling
  • Long‑form content generation
  • Research prototyping

Who it’s for. Developers and researchers needing a large‑context LLM with mixture‑of‑experts capability. Suitable for non‑commercial projects that can accommodate the model’s memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.8 GB 8.4 GB
Too big Get file →
IQ3_XS7.6 GB 9.2 GB
Too big Get file →
Q3_K_S8.0 GB 9.6 GB
Too big Get file →
IQ3_S8.0 GB 9.6 GB
Too big Get file →
IQ3_M8.2 GB 9.8 GB
Too big Get file →
Q3_K_M8.9 GB 10.5 GB
Too big Get file →
Q3_K_L9.6 GB 11.2 GB
Too big Get file →
IQ4_XS10.0 GB 11.6 GB
Too big Get file →
Q4_K_S10.5 GB 12.1 GB
Too big Get file →
Q4_K_M11.2 GB 12.8 GB
Too big Get file →
Q5_K_S12.8 GB 14.3 GB
Too big Get file →
Q5_K_M13.1 GB 14.7 GB
Too big Get file →
Q6_K15.2 GB 16.8 GB
Too big Get file →
Q8_019.7 GB 21.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (6.8 GB file, 8.4 GB memory) or IQ3_XS (7.6 GB file, 9.2 GB memory). For 12 GB VRAM, Q4_K_S (10.54 GB file, 12.1 GB memory) or Q4_K_M (11.2 GB file, 12.8 GB memory) are suitable. Higher quants require more VRAM.

What GPU do you need for NaruMOE-3x7B-v2?

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: the best quant that fits is IQ4_XS (10.0 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (13.1 GB file, about 14.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (19.7 GB file, about 21.3 GB in use).

Which NaruMOE-3x7B-v2 quant should you choose?

Q4_K_M is the usual starting point for NaruMOE-3x7B-v2: it balances file size and quality well. Here it is a 11.2 GB file.

The Q8_0 file is 19.7 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 Q2_K at 6.8 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
Parameters18.5B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyNarumoe
Downloads (HF)1,152
Last updated2024-06-03

Frequently asked questions about NaruMOE-3x7B-v2

How much VRAM does NaruMOE-3x7B-v2 need?

About 12.8 GB at Q4_K_M with an 8K context window. That is the 11.2 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 NaruMOE-3x7B-v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NaruMOE-3x7B-v2 GGUF?

It depends on the quant: Q2_K is 6.8 GB, IQ3_XS is 7.6 GB, Q3_K_S is 8.0 GB, IQ3_S is 8.0 GB, IQ3_M is 8.2 GB, Q3_K_M is 8.9 GB and 8 more.

What context length does NaruMOE-3x7B-v2 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 NaruMOE-3x7B-v2 GGUF?

The files are on Hugging Face in the mradermacher/NaruMOE-3x7B-v2-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 NaruMOE-3x7B-v2 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Q2_K or IQ3_XS; both fit within 8 GB VRAM with approximate memory usage of 8.4 GB and 9.2 GB respectively.

Does this model support vision tasks?

No, the model is text‑only and does not include vision capabilities.

Is the model free for commercial use?

No, it is licensed under CC‑BY‑NC‑4.0, which prohibits commercial use.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Narumoe models

All Narumoe →

Other medium models

All medium models →