Switchboard Router 0.5B v0.1 has 0.494 billion total parameters. The selected F16 GGUF file is 0.994 GB.
Data snapshot: . 1 published test in this catalog.
Model file and details
Provider
Switchboard
Total parameters
494,032,768
Exact file size
994,156,416 bytes
Quantization / precision
F16
Weight repository
switchboardllm/switchboard-router-0.5b-GGUF
Original model repository
switchboardllm/switchboard-router-0.5b
Weight revision
70ee930fab6c041ac34910b141c6269cbf27d280
Model revision
ec0377befc7820dfde29df236e4536253e5fcad0
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-12
Date evidence
The official Apache-2.0 source checkpoint and same-publisher F16 GGUF were created on 12 October 2026. The source card was revised later that day to document the 512-token input boundary and prompt-injection limitation; only README.md changed between pinned source revisions, while the source weights and selected GGUF remained byte-identical.
These scores were compiled from the linked sources. These published scores were not independently tested here. Different prompts, precision, thinking budgets and tools can change results.
Switchboard v0.1 · Tier accuracy
60.3 / 100
Publisher-reported exact three-tier routing accuracy on 10,000 held-out prompts from routellm/gpt4_dataset. This specialist routing result is not a general language-model quality score.
Benchmark efficiency: 60.654 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: Publisher evaluation of Switchboard v0.1 on 10,000 held-out prompts from routellm/gpt4_dataset using three labels: small, mid and frontier. Tier accuracy is the share matching the dataset-derived target tier.
Publisher result, not an independent evaluation. The labels derive from 2023 Mixtral-8x7B answers scored 1-5 by a GPT-4 judge rather than human preferences; the dataset is mostly English. The same evaluation reports 94.5% served-well under its proxy, 5.5% sent too low and 0 invalid JSON outputs, but those are not catalog scores. The selected 994,156,416-byte F16 GGUF was separately tested by the publisher with Ollama at temperature 0 on 347 held-out prompts: it matched the full-precision tier on 347/347 prompts in order and 346/347 shuffled, and produced valid JSON on 347/347. These checks do not establish speed on arbitrary hardware. The card's approximate 1.3 GB in-use memory and 300 ms desktop-CPU timing are publisher observations without a fully specified machine, so they are not treated as universal requirements or performance. The model was trained on prompts cut to 512 tokens, routes one prompt rather than a conversation, and must not be used as a security boundary because a prompt can attempt to influence its tier. Its domain label is a keyword heuristic. Apache-2.0 license.
Context and version evidence: The repository and file name identify the selected model. Revision hashes are shown above when recorded. Tested context length, full hardware configuration and run date are not consistently recorded in this snapshot. Only settings explicitly stated in each benchmark record are known.
The 0.994 GB figure covers model weights in this file. It excludes the context cache, runtime, operating system and any separate multimodal files. It is not a measured RAM requirement or a token-generation speed.
These complete configurations pass the initial weight-size check for the selected 0.99 GB file. Allow extra memory for context and software. Check the model’s runtime notes and your inference software before buying.
Listing evidence: 2026-09-25. Amazon.com base price visible in an owner-supplied screenshot reviewed 25 Sep 2026; capture time not supplied. Dated reference, not a live quote. Excludes card signup offers, coupons, tax and shipping.
Listing evidence: 2026-10-03. Apple US launch price announced 22 September 2026: USD 1,699. Dated manufacturer reference, not an Amazon offer; tax and shipping may differ.
Listing evidence: 2026-09-24. GMKtec, EVO-X2 / 64GB / 1TB, recorded 22 Sep 2026; exact ASIN capacity identified 24 Sep. This is a dated reference, not a current Amazon price; tax, shipping and bundle contents may differ.
Memory matches are estimates, not tested compatibility or speed. As an Amazon Associate I earn from qualifying purchases.
Confirm model architecture and quantization support in your runner. The selected weights use 0.994 GB; this excludes context cache, runtime buffers and other programs.
These are the first listed tiers that pass our reserve policy, not measured minimum requirements. System RAM and VRAM remain separate. Use the memory tool to change the reserve for your context and runner.