SW

Switchboard Router 32b

SwitchboardGGUF by mradermacherUpdated 2026-10-21
Download on Hugging Face
Parameters32.8B
Context40K
Layers64
Architectureqwen3
Smallest quant12.3 GB
Quick answer

Switchboard Router 32b needs about 22.4 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 12.3 GB (Q2_K) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Switchboard Router 32b – a 32.8B parameter JSON‑router model

Switchboard Router 32b is a 32.8B parameter router that outputs a single line of JSON. It is trained on 40960 context tokens and licensed under Apache‑2.0. The model is available in multiple GGUF quantizations.

Good at

  • Fast JSON routing
  • Low‑cost prompt handling
  • Open‑source weights

Limits

  • No vision support
  • Requires 48 GB GPU for FP8
  • No mixture of experts

Best for

  • API proxy routing
  • Cost‑effective prompt delegation
  • OpenAI‑compatible proxy

Who it’s for. Developers building cost‑aware LLM pipelines who need a lightweight router that can forward prompts to higher‑tier models. The model is suitable for production environments that can host a 48 GB GPU for FP8 inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.3 GB 15.0 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
Q3_K_M16.0 GB 18.6 GB
Too big Get file →
Q3_K_L17.3 GB 20.0 GB
Too big Get file →
IQ4_XS17.9 GB 20.5 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.8 GB 22.4 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.2 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →
Q8_034.8 GB 37.5 GB
Too big Get file →

For 8 GB VRAM use Q2_K (12.34 GB file, 15 GB memory at 8 k context). For 16 GB VRAM use Q4_K_S (18.77 GB file, 21.4 GB memory). For 48 GB VRAM use Q8_0 (34.82 GB file, 37.5 GB memory). Memory estimates are approximate.

What GPU do you need for Switchboard Router 32b?

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 Q2_K (12.3 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.8 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).

Which Switchboard Router 32b quant should you choose?

Q4_K_M is the usual starting point for Switchboard Router 32b: it balances file size and quality well. Here it is a 19.8 GB file.

The Q8_0 file is 34.8 GB, about 1.8 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 12.3 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

Architectureqwen3
Parameters32.8B
Layers64
Trained context40,960 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)636
Last updated2026-10-21

Frequently asked questions about Switchboard Router 32b

How much VRAM does Switchboard Router 32b need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.8 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 Switchboard Router 32b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Switchboard Router 32b GGUF?

It depends on the quant: Q2_K is 12.3 GB, Q3_K_S is 14.4 GB, Q3_K_M is 16.0 GB, Q3_K_L is 17.3 GB, IQ4_XS is 17.9 GB, Q4_K_S is 18.8 GB and 5 more.

What context length does Switchboard Router 32b support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Switchboard Router 32b GGUF?

The files are on Hugging Face in the mradermacher/switchboard-router-32b-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 Switchboard Router 32b 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 Switchboard Router 32b on 8 GB VRAM?

Use the Q2_K quant, which is 12.34 GB and requires about 15 GB memory at 8 k context.

Does the model support vision?

No, the model has no vision capabilities.

What license does it use?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Switchboard models

All Switchboard →

Other medium models

All medium models →