Darwin 27B RSI needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Darwin 27B RSI – a 27B reasoning model trained by self‑generated solutions
Darwin 27B RSI is a 27.3B parameter model built on the Qwen3.5‑27B family. It was trained using recursive self‑improvement, learning only from its own solutions. The model is released under the Apache‑2.0 license and supports a 262144‑token context window.
Good at
- Reasoning tasks
- Graduate‑level science questions
- Decision‑making logic
Limits
- No vision support
- Requires large VRAM for full context
- No human‑written training data
Best for
- Academic research assistants
- Complex problem solving
- Educational tutoring
Who it’s for. Researchers and developers who need a large reasoning engine without external training data. The model is ideal for teams that can run it on high‑memory GPUs and want to experiment with self‑improvement loops.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → |
The Q4_K_M quantization file is 16.81 GB and needs about 19.5 GB of VRAM at 8 k context. For 8 k context on a 24 GB GPU, this quant is suitable. If more memory is available, a higher‑precision quant could be used, but no other quants are provided.
What GPU do you need for Darwin 27B RSI?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (16.8 GB file, about 19.5 GB in use).
Which Darwin 27B RSI quant should you choose?
Q4_K_M is the usual starting point for Darwin 27B RSI: it balances file size and quality well. Here it is a 16.8 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Darwin 27B RSI
How much VRAM does Darwin 27B RSI need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Darwin 27B RSI on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Darwin 27B RSI GGUF?
It depends on the quant: Q4_K_M is 16.8 GB.
What context length does Darwin 27B RSI support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Darwin 27B RSI GGUF?
The files are on Hugging Face in the FINAL-Bench/Darwin-27B-RSI-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Darwin 27B RSI use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Darwin 27B RSI on 8 GB VRAM?
No. The Q4_K_M file requires approximately 19.5 GB of VRAM at 8 k context, so 8 GB is insufficient.
What license does the model use?
Apache‑2.0. The model can be used, modified, and redistributed under this license.
Does the model support vision tasks?
No. The model has no vision capabilities.