Primary use stated or inferred cautiously from official documentation.
DaisyRose 27B
RadixArk multimodal model introduced on November 18. It starts from Qwen3.8-27B and uses reinforcement learning on long agent tasks. It retains image understanding and 256K context; 1M training sessions do not enlarge that limit.
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
Limits and integration
| API ID | RadixArk/DaisyRose-27B |
|---|---|
| Model type | Multimodal · Code · Text and reasoning |
| Access model | Open weights |
| License | Apache 2.0 |
| Deployment | Self-hosted |
| Release | 18 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image |
| Exit | Text |
| Context window | 262,144 tokens |
| maximum output | Text; separate output maximum unpublished |
| Reasoning | Not published |
| Published tools | |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Hugging Face |
Coding, tool use and adaptation to agent environments.
The complete architecture includes vision and multi-token prediction: about 27.8B total parameters. BF16, FP8 and NVFP4 are formats of the same model. Long training tasks do not guarantee reliability in unlimited autonomous sessions.
What it can do
Orientation
Coding, tool use and adaptation to agent environments.
Context
262,144 tokens · Text; separate output maximum unpublished
Tools and integration
Not published
Access
Hugging Face · downloadable checkpoint
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | No published official API rate | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Self-hosted infrastructure cost | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
No verified official API tariff. Self-hosting requires memory, compute and maintenance; downloadable weights do not make inference free.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
How to read the results
RadixArk reports 46.2% on DeepSWE v1.1 with eight repetitions per task and mini-swe-agent, and 90.7% on GPQA Diamond with eight repetitions of 198 questions. The table takes the better of BF16 and FP8; it is not a single-precision result or an Inferama evaluation.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| DeepSWE v1.1 | 46.2 % | Published score | View source ↗ |
| GPQA Diamond | 90.7 % | Published score | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
Chronology
radixark/DaisyRose-27B
Version added to Inferama's verified catalog.