AR

ArrowNeo AME 4x3B v0.1 MoE

ArrowneoGGUF by yasu-ohUpdated 2025-03-30
Download on Hugging Face
Parameters7.76B
Context8K
Layers32
Architecturellama
Smallest quant4.2 GB
Quick answer

ArrowNeo AME 4x3B v0.1 MoE needs about 6.6 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 4.2 GB (IQ4_XS) to 6.4 GB (Q6_K).

ArrowNeo AME 4x3B v0.1 MoE is a 7.76B-parameter Arrowneo model in GGUF format, quantized by yasu-oh. Its trained context length is 8K tokens. The repository has 4 quant files, from 4.2 GB (IQ4_XS) to 6.4 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS4.2 GB 6.0 GB
Fits Get file →
Q4_K_M4.7 GB 6.6 GB
Fits Get file →
Q5_K_M5.5 GB 7.4 GB
Tight Get file →
Q6_K6.4 GB 8.2 GB
Too big Get file →

What GPU do you need for ArrowNeo AME 4x3B v0.1 MoE?

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 IQ4_XS (4.2 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.5 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 8.2 GB in use).

Which ArrowNeo AME 4x3B v0.1 MoE quant should you choose?

Q4_K_M is the usual starting point for ArrowNeo AME 4x3B v0.1 MoE: it balances file size and quality well. Here it is a 4.7 GB file.

If memory is tight, the smallest file is IQ4_XS at 4.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.76B (approximate, mixture of experts)
Layers32
Trained context8,192 tokens
KV cache (fp16)160 KB per token

Source

Quantized byyasu-oh
FamilyArrowneo
Licensemit
Downloads (HF)76
Last updated2025-03-30

Frequently asked questions about ArrowNeo AME 4x3B v0.1 MoE

How much VRAM does ArrowNeo AME 4x3B v0.1 MoE need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 4.7 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 ArrowNeo AME 4x3B v0.1 MoE on an 8 GB GPU?

Yes, with Q5_K_M: the 5.5 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ArrowNeo AME 4x3B v0.1 MoE GGUF?

It depends on the quant: IQ4_XS is 4.2 GB, Q4_K_M is 4.7 GB, Q5_K_M is 5.5 GB, Q6_K is 6.4 GB.

What context length does ArrowNeo AME 4x3B v0.1 MoE support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.3 GB at 8K and 1.3 GB at 8K.

Where can I download ArrowNeo AME 4x3B v0.1 MoE GGUF?

The files are on Hugging Face in the yasu-oh/ArrowNeo-AME-4x3B-v0.1-MoE-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 ArrowNeo AME 4x3B v0.1 MoE use?

Hugging Face lists the license as mit. 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 ArrowNeo-AME-4x3B-v0.1-MoE

Similar models

Browse all →

More from yasu-oh

All by yasu-oh →

More Arrowneo models

All Arrowneo →

Other small models

All small models →