MS3.2 24B Magnum Diamond
rsLoRA finetune of a text-only conversion of Mistral Small 3.2 24B Instruct (2506), built to bring the Magnum mix's Claude-like prose to a smaller footprint. The "Diamond" moniker nods to the extra heat and pressure - pre-tokenization plus custom loss masking - to turn the assistant-tuned base into creative-writing gems, with or without character names or prefill.
Added Nov 24, 2025
Pricing
Auto routing · per 1M tokens- Input
- $0.493
- Output
- $0.493
- Cache read
- $0.246
Specifications
- Context window
- 16.4K
- Max output
- 32.8K
- Parameters
- 24B
Benchmarks
Benchmarks
Leaderboard results
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 22.8 | #123 of 149 |
UGI Willingness | 2.2 | #113 of 149 |
UGI Writing | 35.9 | #105 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
 Recommended | $0.493 | $0.493 | $0.246 | N/A | N/A |
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.