FA

Fairy2i W2

FairyGGUF by mradermacherUpdated 2025-12-10
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

Fairy2i W2 needs about 8.9 GB of memory at Q4_K_M (a 4.1 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 5.5 GB (Q6_K).

Fairy2i W2 – 6.74B complex‑valued LLM with 2‑bit quantization

Fairy2i W2 is a 6.74B parameter model based on the Fairy family. It uses a widely‑linear complex transformation to enable extremely low‑bit quantization while preserving full‑precision performance. The model supports a 4096‑token context window.

Good at

  • Low‑bit inference on commodity hardware
  • Preserving LLaMA‑2 7B performance at 2‑bit
  • Efficient multiplication‑free accumulation

Limits

  • No vision support
  • Requires GGUF format
  • License is llama2

Best for

  • Embedded inference
  • Edge devices with limited VRAM
  • Rapid prototyping of complex‑valued models

Who it’s for. Developers and researchers needing efficient inference of large language models on limited hardware. The model is suitable for those who can work with GGUF files and are comfortable with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S1.5 GB 4.2 GB
Fits Get file →
IQ1_M1.7 GB 4.3 GB
Fits Get file →
IQ2_XXS1.9 GB 4.5 GB
Fits Get file →
IQ2_XS2.0 GB 4.7 GB
Fits Get file →
IQ2_S2.2 GB 4.8 GB
Fits Get file →
Q2_K_S2.3 GB 5.0 GB
Fits Get file →
IQ2_M2.4 GB 5.0 GB
Fits Get file →
Q2_K2.5 GB 5.2 GB
Fits Get file →
IQ3_XXS2.6 GB 5.2 GB
Fits Get file →
IQ3_XS2.8 GB 5.4 GB
Fits Get file →
IQ3_S2.9 GB 5.6 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
IQ3_M3.1 GB 5.8 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
IQ4_XS3.6 GB 6.3 GB
Fits Get file →
IQ4_NL3.8 GB 6.5 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q4_14.2 GB 6.9 GB
Fits Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS (2.03 GB, 6.8 GB memory) or Q2_K_S (2.32 GB, 7.1 GB memory). If 12 GB VRAM is available, IQ3_S (2.95 GB, 7.7 GB memory) or Q3_K_M (3.3 GB, 8.1 GB memory) provide higher quality. Memory estimates are approximate.

What GPU do you need for Fairy2i W2?

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 the main file (0.0 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).

Which Fairy2i W2 quant should you choose?

Q4_K_M is the usual starting point for Fairy2i W2: it balances file size and quality well. Here it is a 4.1 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

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyFairy
Licensellama2
Downloads (HF)1,091
Last updated2025-12-10

Frequently asked questions about Fairy2i W2

How much VRAM does Fairy2i W2 need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Fairy2i W2 on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Fairy2i W2 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB and 19 more.

What context length does Fairy2i W2 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Fairy2i W2 GGUF?

The files are on Hugging Face in the mradermacher/Fairy2i-W2-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 Fairy2i W2 use?

Hugging Face lists the license as llama2. 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 Fairy2i W2 on 8 GB VRAM?

Yes, the IQ2_XS quant (2.03 GB file, 6.8 GB memory) fits within 8 GB VRAM.

Does the model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of Fairy2i-W2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Fairy models

All Fairy →

Other small models

All small models →