Model details
Skyfall 36B V2
Skyfall 36B V2 is a fine-tuned variant of Mistral Small, positioned by its creator as a model tuned specifically for creative and interactive writing tasks. Rather than targeting general reasoning or broad assistant behavior, the fine-tuning work emphasizes enhanced creativity, nuanced storytelling, and immersive roleplay, making the model a strong fit for applications centered on fictional characters, dialogue, and narrative-driven interaction. This lineage from Mistral Small means the model inherits that base's general language understanding while layering stylistic and character-oriented behavior on top, which is the core differentiator compared with more general-purpose chat models.
In practical terms, Skyfall 36B V2 is best suited to writers, game masters, interactive-fiction developers, and anyone building roleplay experiences where character voice, emotional depth, and story coherence matter more than raw analytical precision. Its positioning alongside other narrative-focused models in the same release cohort suggests an emphasis on sustaining long, consistent character portrayals across multi-turn exchanges. Teams evaluating it for production use should weigh it against other storytelling-oriented open models, focusing prompts and evaluation criteria on creativity, persona stability, and narrative quality rather than on code or math benchmarks.
Quick Info
Powered by- Provider
- AI/ML API
- Model key
- thedrummer/skyfall-36b-v2
- Release date
- Mar 10, 2025
- Last updated
- Mar 10, 2025
- Knowledge cutoff
- 2024-06-30
- Input modalities
- Output modalities
- Capabilities
Cost
- Input token cost
- $0.75647
- Output token cost
- $1.10032
Limits
- Output tokens
- 32,768 tokens
- Context window
- 32,768 tokens
Latest news about Skyfall 36B V2
We haven't found any news about Skyfall 36B V2 yet. New models can take a few days to get coverage, so check back soon or look again now.
