Qwen3.5 4B SoraEyeAI needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.7 GB (Q4_K_M) to 3.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Qwen3.5 4B SoraEyeAI – on‑device vision‑language model for Japanese walking assistance
Qwen3.5 4B SoraEyeAI is a fine‑tuned Qwen3.5‑4B model that describes surroundings in short Japanese sentences. It runs entirely on the device, using the iPhone’s camera and internal memory. The model supports reasoning, tools, and vision.
Good at
- Vision‑language description in Japanese
- On‑device inference
- Short contextual explanations
Limits
- No external vision data transfer
- Requires iPhone 15 Pro or newer
- Limited to 8 k context
Best for
- Assistive walking companion
- On‑device photo description
- Japanese text narration
Who it’s for. Developers building assistive apps for visually impaired users on iOS. The model is free under Apache 2.0 and can be integrated into iPhone applications that need real‑time vision‑language output.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 5.0 GB | Fits | Get file → |
The only available quantization is Q6_K with a file size of 3.46 GB. It requires approximately 5 GB of RAM at 8 k context. For 8 GB VRAM devices, this quant is suitable and will fit comfortably.
What GPU do you need for Qwen3.5 4B SoraEyeAI?
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 Q6_K (3.5 GB file, about 5.0 GB in use).
Which Qwen3.5 4B SoraEyeAI quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 4B SoraEyeAI: it balances file size and quality well. Here it is a 2.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.5 4B SoraEyeAI
How much VRAM does Qwen3.5 4B SoraEyeAI need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Qwen3.5 4B SoraEyeAI on an 8 GB GPU?
Yes, with Q6_K: the 3.5 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 4B SoraEyeAI GGUF?
It depends on the quant: Q4_K_M is 2.7 GB, Q6_K is 3.5 GB.
What context length does Qwen3.5 4B SoraEyeAI support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Qwen3.5 4B SoraEyeAI GGUF?
The files are on Hugging Face in the nori-sdc/Qwen3.5-4B-SoraEyeAI-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 Qwen3.5 4B SoraEyeAI 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 Qwen3.5 4B SoraEyeAI on a device with 8 GB VRAM?
Yes, the Q6_K quant uses about 5 GB of RAM at 8 k context, so it fits within 8 GB VRAM.
What iPhone models can run SoraEyeAI?
iPhone 15 Pro and newer models are required, as they provide the 8 GB memory needed for the model.
Does the model send photos outside the device?
No, all image processing occurs on the iPhone; photos are not transmitted or stored externally.