AQ

Aquif 3.5 A4B Think

AquifGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters12.1B
Context128K
Layers36
Architectureqwen3moe
Smallest quant0.0 GB
Quick answer

Aquif 3.5 A4B Think needs about 9.1 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 9.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Aquif 3.5 A4B Think – a 12.1B parameter Qwen3MOE model

Aquif 3.5 A4B Think is a 12.1B parameter Qwen3MOE architecture with 4B active parameters. It supports reasoning and tool usage. The model is released under the apache-2.0 license.

Good at

  • Reasoning tasks
  • Tool integration
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • No external training data provided

Best for

  • Chatbots needing reasoning
  • Tool‑enabled assistants
  • Long‑form content generation

Who it’s for. Developers building AI assistants that require reasoning and tool usage. The model is suitable for users with sufficient GPU memory to run higher‑quality quants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ1_S2.7 GB 4.4 GB
Fits Get file →
IQ1_M2.9 GB 4.6 GB
Fits Get file →
IQ2_XXS3.3 GB 5.1 GB
Fits Get file →
IQ2_XS3.7 GB 5.4 GB
Fits Get file →
IQ2_S3.8 GB 5.5 GB
Fits Get file →
IQ2_M4.1 GB 5.8 GB
Fits Get file →
Q2_K_S4.3 GB 6.0 GB
Fits Get file →
Q2_K4.6 GB 6.3 GB
Fits Get file →
IQ3_XXS4.8 GB 6.5 GB
Fits Get file →
IQ3_XS5.1 GB 6.8 GB
Fits Get file →
Q3_K_S5.4 GB 7.1 GB
Fits Get file →
IQ3_S5.4 GB 7.1 GB
Fits Get file →
IQ3_M5.5 GB 7.2 GB
Fits Get file →
Q3_K_M5.9 GB 7.6 GB
Tight Get file →
Q3_K_L6.4 GB 8.1 GB
Too big Get file →
IQ4_XS6.6 GB 8.3 GB
Too big Get file →
IQ4_NL6.9 GB 8.6 GB
Too big Get file →
Q4_06.9 GB 8.6 GB
Too big Get file →
Q4_K_S7.0 GB 8.7 GB
Too big Get file →
Q4_K_M7.4 GB 9.1 GB
Too big Get file →
Q4_17.6 GB 9.3 GB
Too big Get file →
Q5_K_S8.4 GB 10.1 GB
Too big Get file →
Q5_K_M8.6 GB 10.3 GB
Too big Get file →
Q6_K9.9 GB 11.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.67 GB, memory 4.4 GB). For 12 GB VRAM, IQ2_S (3.79 GB, 5.5 GB) or Q2_K (4.59 GB, 6.3 GB). For 16 GB VRAM, Q4_K_M (7.38 GB, 9.1 GB) or Q5_K_M (8.62 GB, 10.3 GB). Memory estimates are approximate.

What GPU do you need for Aquif 3.5 A4B Think?

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: the best quant that fits is the main file (0.0 GB file, about 1.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q2_K_S (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (5.9 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (9.9 GB file, about 11.6 GB in use).

Which Aquif 3.5 A4B Think quant should you choose?

Q4_K_M is the usual starting point for Aquif 3.5 A4B Think: it balances file size and quality well. Here it is a 7.4 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters12.1B (approximate, mixture of experts)
Active parameters4B
Layers36
Trained context131,072 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyAquif
Licenseapache-2.0
Downloads (HF)655
Last updated2025-12-04

Frequently asked questions about Aquif 3.5 A4B Think

How much VRAM does Aquif 3.5 A4B Think need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 7.4 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 Aquif 3.5 A4B Think on an 8 GB GPU?

Yes, with Q3_K_M: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Aquif 3.5 A4B Think GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.7 GB, IQ1_M is 2.9 GB, IQ2_XXS is 3.3 GB, IQ2_XS is 3.7 GB, IQ2_S is 3.8 GB and 19 more.

What context length does Aquif 3.5 A4B Think support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Aquif 3.5 A4B Think GGUF?

The files are on Hugging Face in the mradermacher/aquif-3.5-A4B-Think-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 Aquif 3.5 A4B Think 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 Aquif 3.5 A4B Think on 8 GB VRAM?

Yes, using the IQ1_S quant which requires about 4.4 GB of VRAM at 8k context.

Does the model support vision?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Aquif models

All Aquif →

Other medium models

All medium models →