Cydonia 24B V4.1
Summary
Cydonia 24B V4.1 is an open-weight language model from Thedrummer, released on 27 Sept 2025. It accepts text and generates text, with a 131K-token context window and up to 118K output tokens per response.
Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.
Last verified 19 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Thedrummer |
|---|---|
| Release date | 27 Sept 2025 [OpenRouter] |
| Status | Generally available |
| Weights | Open weights [Hugging Face] |
| Parameters | 23.6B [Hugging Face] |
| Context window | 131K (131,072 tokens) [OpenRouter] |
| Max output | 118K tokens [OpenRouter] |
| Knowledge cutoff | 30 Apr 2024 [OpenRouter] |
| Input | Text [OpenRouter] |
| Output | Text [OpenRouter] |
| Reasoning mode | No [OpenRouter] |
| Tool calling | No [OpenRouter] |
| Structured output | Yes [OpenRouter] |
| Hugging Face | thedrummer/cydonia-24b-v4.1 [Hugging Face] |
Cydonia 24B V4.1 API pricing by provider
USD per million tokens. Sorted by input price.
We do not currently track a paid API listing for this model.
Running Cydonia 24B V4.1 locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 14 GB | 16 GB | 20 GB |
| Q8_0 (8-bit) | 25 GB | 27 GB | 31 GB |
| FP16 / BF16 (16-bit) | 47 GB | 49 GB | 53 GB |
At 4-bit with an 8K conversation, Cydonia 24B V4.1 needs about 16 GB, so it fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.
Frequently asked questions
What is the context window of Cydonia 24B V4.1?
Cydonia 24B V4.1 has a context window of 131,072 tokens (131K) and can generate up to 117,964 tokens in a single response, according to OpenRouter.
Is Cydonia 24B V4.1 open source?
Cydonia 24B V4.1 is an open-weight model: its weights are published on Hugging Face as thedrummer/cydonia-24b-v4.1. Check the license terms before commercial use.
When was Cydonia 24B V4.1 released?
Thedrummer released Cydonia 24B V4.1 on 27 Sept 2025, according to OpenRouter.
How much VRAM does Cydonia 24B V4.1 need?
About 16 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 27 GB at 8-bit. The 4-bit model fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Qwen3 VL 235B A22B Thinking | Alibaba (Qwen) | 23 Sept 2025 | 131K | $0.98 | $3.95 | Open |
| Granite-4.0-H-Small | IBM | 2 Oct 2025 | 131K | – | – | Open |
| Granite 4.0 H Micro | IBM | 2 Oct 2025 | 131K | $0.02 | $0.11 | Open |
| Gemma Sea Lion V4 27B It | Aisingapore | 23 Sept 2025 | 128K | $0.35 | $0.56 | Open |
| Magistral Small 1.2 | Mistral AI | 18 Sept 2025 | 128K | $0.50 | $1.50 | Open |
| Qwen3 VL 8B Thinking | Alibaba (Qwen) | 14 Oct 2025 | 131K | – | – | Open |
Change history
- No longer listed on openrouter