Darwin 27B RSI needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.7 GB (Q2_K) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Darwin 27B RSI – a 27B Qwen3.5‑based reasoning model
Darwin 27B RSI is a 27B dense Qwen3.5 model trained with recursive self‑improvement. It improves on graduate‑level science reasoning without human‑written solutions. The model is released under Apache‑2.0 and supports 262144 context tokens.
Good at
- Reasoning
- Graduate‑level science
- Self‑improvement
Limits
- No vision support
- Requires large VRAM for full precision
- License is Apache‑2.0
Best for
- Academic research on reasoning
- Benchmarking self‑improvement loops
- Developing reasoning‑heavy applications
Who it’s for. Researchers and developers who need a large reasoning model that has been improved through self‑learning. The model is suitable for use cases that require deep logical analysis and can run on systems with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.7 GB | 13.4 GB | Too big | Get file → | |
| Q3_K_S | 12.1 GB | 14.7 GB | Too big | Get file → | |
| Q3_K_M | 13.3 GB | 15.9 GB | Too big | Get file → | |
| Q3_K_L | 14.3 GB | 17.0 GB | Too big | Get file → | |
| IQ4_XS | 15.2 GB | 17.8 GB | Too big | Get file → | |
| Q4_K_S | 15.6 GB | 18.2 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 19.2 GB | Too big | Get file → | |
| Q5_K_S | 18.7 GB | 21.3 GB | Too big | Get file → | |
| Q5_K_M | 19.2 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 22.1 GB | 24.7 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 31.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (10.71 GB) or Q3_K_S (12.07 GB). For 12 GB VRAM, Q3_K_M (13.3 GB) or Q4_K_S (15.59 GB) are suitable. For 16 GB VRAM, Q4_K_M (16.55 GB) or Q5_K_S (18.68 GB) provide a balance of size and performance. Estimates are approximate.
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: the best quant that fits is Q3_K_M (13.3 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 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 16.5 GB file.
The Q8_0 file is 28.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 10.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 13.4 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: Q2_K is 10.7 GB, Q3_K_S is 12.1 GB, Q3_K_M is 13.3 GB, Q3_K_L is 14.3 GB, IQ4_XS is 15.2 GB, Q4_K_S is 15.6 GB and 5 more.
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 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Darwin 27B RSI GGUF?
The files are on Hugging Face in the mradermacher/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?
Yes, the Q2_K quant is 10.71 GB and estimated memory at 8k context is 13.4 GB, which is close to 8 GB VRAM limits. It may require swapping or lower context.
Does the model support vision tasks?
No, the model has no vision support and is purely text‑based.
What license applies to this model?
The model is released under the Apache‑2.0 license.