Cydonia 24B V4.1
TheDrummer · released Aug 17, 2025 · thedrummer/cydonia-24b-v4.1
- Type
- Open weights
- Params
- 23.6B
- Context
- 131K
about 98K words of context
Our take
Written Aug 11, 2026Cydonia is a 23.6-billion-parameter text model from TheDrummer with a 131,072-token request limit and flat pricing across its two hosted endpoints. Its weights are marked as open, though licence terms remain unverified in our data.
Pick this for budget-conscious text work where open weights matter more than measured quality, or for long-context drafting at 131K tokens. Use it if you want identical pricing across providers with no shopping friction. Skip it if you need benchmark scores, confirmed licence terms, or verified throughput on every endpoint.
The case for it
- Identical pricing across both providers eliminates shopping friction.
- Open weights enable local deployment and modification.
- Output pricing sits well under a dollar per million tokens for a 23.6-billion-parameter model.
The case against it
- No benchmark scores in our data — no Elo, MMLU or task scores to judge quality by.
- Throughput unknown on one of two endpoints; only Parasail reports 38 tokens per second.
- Licence terms unverified despite the open-weights flag.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 5.9 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 13.9 GB spare means a 10% error in the size would not change the answer.
Apple M2 (10-core GPU) · 24 GB
Borderline fit on an estimated size. It leaves 1.1 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 2 hours ago — each listing carries its own date.
- per 1M tokens
- $0.30 in / $0.50 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.30 / $0.50checked 2 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| Parasailbf16Through OpenRouter | $0.30 / $0.50checked 2 hours ago | 131K118K max reply | 15 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✓ |
| Parasailbf16Through OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model yet.
Identifiers
- Hugging Face
- thedrummer/cydonia-24b-v4.1
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- thedrummer-cydonia-24b-v4-1