Magnum v4 72B is Anthracite Org's model. Its measured tokenizer sits with the Qwen group, which is evidence that it builds on the Qwen tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Anthracite Org's authorship of the model itself.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 36 other models | tk_5410b38e |
| API surface | No other entry shares this exact contract | api_9236c18f |
| Context and output | 32,768 context · 4,096 max output | declared |
| Reasoning contract | None declared | declared |
| Serving providers observed | Mancer 2 | measured 3 September 2026 |
Click a row to open the full comparison.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 8 prompt tokens.
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).
Supported parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_atop_ktop_logprobstop_p
defaults: {}
Cite this page as the evidence record for Magnum v4 72B: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.
