SW

Swish 31B Final

SwishGGUF by mradermacherUpdated 2026-10-26
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant11.9 GB
Quick answer

Swish 31B Final needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 11.9 GB (Q2_K) to 32.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Swish 31B Final – a 30.7B‑parameter gemma4 model with reasoning, roleplay, tools, and vision abilities

Swish 31B Final is a 30.7B‑parameter model based on the gemma4 architecture. It supports reasoning, roleplay, tools, and vision. The model is released under the Apache‑2.0 license.

Good at

  • Reasoning and complex dialogue
  • Tool usage and instruction following
  • Vision‑enabled image understanding

Limits

  • No vision support in GGUF quant files
  • Large VRAM requirement for 8k context
  • No mixture‑of‑experts architecture

Best for

  • Chatbots requiring multimodal input
  • AI assistants that need tool integration
  • Image‑based question answering

Who it’s for. Developers and researchers building multimodal LLM applications who need a large, versatile model. The model is suitable for environments with sufficient GPU memory and for projects that can handle the 8k context length.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.9 GB 44.6 GB
Too big Get file →
Q3_K_S13.8 GB 46.5 GB
Too big Get file →
Q3_K_M15.3 GB 48.0 GB
Too big Get file →
Q3_K_L16.6 GB 49.3 GB
Too big Get file →
IQ4_XS16.9 GB 49.6 GB
Too big Get file →
Q4_K_S17.8 GB 50.5 GB
Too big Get file →
Q4_K_M18.7 GB 51.4 GB
Too big Get file →
Q5_K_S21.3 GB 54.0 GB
Too big Get file →
Q5_K_M21.8 GB 54.6 GB
Too big Get file →
Q6_K25.2 GB 57.9 GB
Too big Get file →
Q8_032.6 GB 65.3 GB
Too big Get file →

For 48 GB VRAM, use Q3_K_S (file size 13.76 GB, estimated 46.5 GB memory). For 64 GB VRAM, Q4_K_S (17.76 GB, 50.5 GB memory) or Q4_K_M (18.69 GB, 51.4 GB memory). Smaller quants such as Q2_K require 44.6 GB memory and are suitable only on GPUs with >44 GB VRAM. Estimates are approximate.

What GPU do you need for Swish 31B Final?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q3_K_M (15.3 GB file, about 48.0 GB in use).

Which Swish 31B Final quant should you choose?

Q4_K_M is the usual starting point for Swish 31B Final: it balances file size and quality well. Here it is a 18.7 GB file.

The Q8_0 file is 32.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 11.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized bymradermacher
FamilySwish
Licenseapache-2.0
Downloads (HF)1,526
Last updated2026-10-26

Frequently asked questions about Swish 31B Final

How much VRAM does Swish 31B Final need?

About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 Swish 31B Final on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Swish 31B Final GGUF?

It depends on the quant: Q2_K is 11.9 GB, Q3_K_S is 13.8 GB, Q3_K_M is 15.3 GB, Q3_K_L is 16.6 GB, IQ4_XS is 16.9 GB, Q4_K_S is 17.8 GB and 5 more.

What context length does Swish 31B Final support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download Swish 31B Final GGUF?

The files are on Hugging Face in the mradermacher/Swish-31B-Final-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 Swish 31B Final 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 Swish 31B Final on a GPU with 8 GB VRAM?

No. The smallest quant requires 44.6 GB VRAM at 8k context. 8 GB VRAM is insufficient.

Does the model support vision tasks?

Yes, the model has vision abilities, but the GGUF quant files do not include a vision tokenizer. Vision support requires additional configuration.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Swish-31B-Final

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Swish models

All Swish →

Other medium models

All medium models →