Model comparison
Magnum v4 72B vs Claude 4 Sonnet
Capability radar, value bars, and side-by-side posture.
Magnum v4 72B
Not scored
value score
Claude 4 Sonnet
91
value score
Magnum v4 72B ctx
—
Claude 4 Sonnet ctx
200K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Claude 4 Sonnet91
Attribute tape
| Field | Magnum v4 72B | Claude 4 Sonnet |
|---|---|---|
| Developer | Anthracite | Anthropic |
| Context | — | 200K |
| Modalities | Text, Code, Image | |
| Openness | — | Proprietary Model |
| Speed | — | Fast |
| Price | — | $3/1M in · $15/1M out |
| Value score | — | 91 |
| Summary | Magnum v4 72B is a 72-billion-parameter open-weight language model from Anthracite, fine-tuned on Qwen2.5-72B-Instruct and optimized for creative writing, roleplay, and character-driven narrative prose. It targets Claude 3 Sonnet/Opus-style prose quality while remaining a fully open, Anthracite-published fine-tune. | Balanced Claude model for coding and agents. |