SW

swift15 gsq rco iq3s mtp

SwiftGGUF by jonathan-goldenUpdated 2026-09-25
Download on Hugging Face
Parameters461M
Context256K
Layers65
Architectureqwen35
Smallest quant12.1 GB
Quick answer

swift15 gsq rco iq3s mtp needs about 14.8 GB of memory at IQ3_S (a 12.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Swift15 GSQ RCO IQ3S MTP – a compact vision‑enabled Qwen‑35 model

Swift15 GSQ RCO IQ3S MTP is a 0.461 billion‑parameter Qwen‑35 model quantized to IQ3_S. It supports vision tasks and was trained on a 262144‑token context window. The model is released under an other license.

Good at

  • Vision inference
  • Small footprint
  • Fast loading

Limits

  • Requires ~14.8 GB VRAM at 8k context
  • No explicit language support listed
  • License is other, not open source

Best for

  • Low‑resource vision inference
  • Rapid prototyping of vision‑enabled LLMs
  • Embedded vision applications

Who it’s for. Developers and researchers who need a lightweight vision‑capable LLM that can run on modest hardware. The model is suitable for edge deployments where memory is limited but vision functionality is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S12.1 GB 14.8 GB
Too big Get file →

For 8 GB VRAM, the IQ3_S quant is too large; it needs about 14.8 GB. If you have 16 GB VRAM, IQ3_S will fit. No other quantizations are available for this model.

What GPU do you need for swift15 gsq rco iq3s mtp?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ3_S (12.1 GB file, about 14.8 GB in use).

Which swift15 gsq rco iq3s mtp quant should you choose?

IQ3_S (12.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters461M
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized byjonathan-golden
FamilySwift
Licenseother
Downloads (HF)154
Last updated2026-09-25

Frequently asked questions about swift15 gsq rco iq3s mtp

How much VRAM does swift15 gsq rco iq3s mtp need?

About 14.8 GB at IQ3_S with an 8K context window. That is the 12.1 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 swift15 gsq rco iq3s mtp on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of swift15 gsq rco iq3s mtp GGUF?

It depends on the quant: IQ3_S is 12.1 GB.

What context length does swift15 gsq rco iq3s mtp support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.

Where can I download swift15 gsq rco iq3s mtp GGUF?

The files are on Hugging Face in the jonathan-golden/swift15-gsq-rco-iq3s-mtp repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does swift15 gsq rco iq3s mtp use?

Hugging Face lists the license as other. 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?

No. The IQ3_S quant requires about 14.8 GB VRAM at 8k context, so 8 GB is insufficient.

What license does this model use?

The model is released under an other license; check the repository for specific terms.

Does the model support vision?

Yes, the model has detected vision abilities and can process image inputs.

Similar models

Browse all →

More from jonathan-golden

All by jonathan-golden →

More Swift models

All Swift →

Other tiny models

All tiny models →