Olala Mini 7A1B vs Dhīr 5B MoE vs DaisyRose-27B
No independent capability benchmark covers every model here yet. The score uses context window.
Price in rating: Included · Exclude price
OVHcloud
Olala Mini 7A1B
10/100- ECI—
- Price—
- Context32K
ZenteiQ
Dhīr 5B MoE
0/100- ECI—
- Price—
- Context16K
RadixArk
DaisyRose-27B
43/100- ECI—
- Price—
- Context262K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (DaisyRose-27B 43/100, Olala Mini 7A1B 10/100, Dhīr 5B MoE 0/100) compare the available specifications and price. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Longest contextDaisyRose-27BDaisyRose-27B 262,144 · Olala Mini 7A1B 32,000 · Dhīr 5B MoE 16,384 tokens
- Widest inputsDaisyRose-27BOlala Mini 7A1B: Text · Dhīr 5B MoE: Text · DaisyRose-27B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Olala Mini 7A1B | Dhīr 5B MoE | DaisyRose-27B |
|---|---|---|---|---|
| Context window | 100% | 10 | 0 | 43 |
| Specs & price only | 100% | 10/100 | 0/100 | 43/100 |
Left out because at least one model lacks the data: capability, price and inputs & features. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Task | Multilingual language generation | Multilingual assistant | Agentic coding |
| Published capabilities | Compact mixture-of-experts model combining hybrid attention and Mamba layers. | Mixture-of-experts assistant supporting English and ten Indian languages for offline deployment. | Post-trained from Qwen3.8-27B on 1,200 agent tasks. RadixArk reports 12% pass@1 on Terminal-Bench 4.1. |
| Model size | 7B total / 1B active | 5.09B total / 1.79B active | 27B parameters |
| Access | Downloadable checkpoint for local inference or fine-tuning | Open weights for on-premises or offline use | Public BF16, FP8 and NVFP4 checkpoints |
| Sources | Model weights · Additional documentation | Publisher documentation · Additional documentation | Publisher documentation |
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | — | — | — |
| Output | — | — | — |
| Cached input | — | — | — |
| Blended (3:1) | — | — | — |
| Long-context rate | — | — | — |
| Price source | — | — | — |
| Limits | |||
| Context window | 32,000 tokens | 16,384 tokens | 262,144 tokens (best) |
| Max output | — | — | — |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Unconfirmed | Unconfirmed | Unconfirmed |
| Tool calling | Yes | — | — |
| Structured output | — | — | — |
| Availability | |||
| Weights | OpenApache-2.0 | Open | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | — | — | — |
| Released | Nov 19, 2026 | Nov 3, 2026 | Nov 18, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Olala Mini 7A1B—
Dhīr 5B MoE—
DaisyRose-27B—
Which should you choose?
Which is better: Olala Mini 7A1B, Dhīr 5B MoE or DaisyRose-27B?
There is not enough shared capability evidence to name an overall winner. The scores (DaisyRose-27B 43/100, Olala Mini 7A1B 10/100, Dhīr 5B MoE 0/100) compare the available specifications and price. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Olala Mini 7A1B, Dhīr 5B MoE or DaisyRose-27B?
None of these models has a published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Olala Mini 7A1B has not been scored yet, Dhīr 5B MoE has not been scored yet and DaisyRose-27B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Olala Mini 7A1B, Dhīr 5B MoE and DaisyRose-27B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Dhīr 5B MoE and DaisyRose-27B has no confirmed tool-calling support in this comparison.
Which has the bigger context window?
DaisyRose-27B has the largest context window at 262,144 tokens, against 32,000 for Olala Mini 7A1B and 16,384 for Dhīr 5B MoE.
Which can read images, PDFs, audio or video?
Olala Mini 7A1B accepts text; Dhīr 5B MoE accepts text; DaisyRose-27B accepts text and images. DaisyRose-27B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0), so you can self-host them.
Which is newer?
Olala Mini 7A1B is the newest, released Nov 19, 2026. DaisyRose-27B came out Nov 18, 2026; Dhīr 5B MoE came out Nov 3, 2026.
How do you decide the winner?
This rating uses context window (100%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 19, 2026.