DiscoveryRSI 27B 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. This repository has 15 quants, from 0.0 GB to 22.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
DiscoveryRSI 27B – a 27.3B‑parameter research ideation model
DiscoveryRSI 27B is a 27.3B‑parameter language model fine‑tuned for scientific research ideation and evidence‑grounded planning. It supports hypothesis generation, experiment evaluation, and iterative revision within the DiscoveryRSI harness.
Good at
- Hypothesis generation
- Experiment evaluation
- Research planning
Limits
- Requires large VRAM – 13.5GB+ at 8k context
- No vision support
- Apache‑2.0 license
Best for
- Research ideation
- Hypothesis evaluation
- Evidence‑grounded planning
Who it’s for. Researchers and developers building research‑support tools. The model is intended for use within the DiscoveryRSI agentic harness and is not a medical device. Generated hypotheses require expert review.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| Q2_K | 10.9 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_S | 12.3 GB | 14.9 GB | Too big | Get file → | |
| IQ3_S | 12.6 GB | 15.3 GB | Too big | Get file → | |
| IQ3_M | 12.8 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_L | 14.6 GB | 17.2 GB | Too big | Get file → | |
| IQ4_XS | 15.3 GB | 18.0 GB | Too big | Get file → | |
| Q4_0 | 15.8 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_S | 15.8 GB | 18.5 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| Q4_1 | 17.3 GB | 20.0 GB | Too big | Get file → | |
| Q5_K_S | 19.0 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 19.5 GB | 22.2 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → |
For 8GB VRAM none of the quants fit – the smallest quant (Q2_K) needs 13.5GB at 8k context. For 16GB VRAM, Q4_K_M (19.5GB) is still too large; consider Q4_0 (18.4GB) or Q5_K_S (21.7GB) if you can allocate more memory. The Q2_K quant offers the lowest memory usage at 13.5GB, but still exceeds 8GB.
What GPU do you need for DiscoveryRSI 27B?
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: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (12.8 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 22.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.4 GB file, about 25.1 GB in use).
Which DiscoveryRSI 27B quant should you choose?
Q4_K_M is the usual starting point for DiscoveryRSI 27B: it balances file size and quality well. Here it is a 16.8 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DiscoveryRSI 27B
How much VRAM does DiscoveryRSI 27B 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 DiscoveryRSI 27B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DiscoveryRSI 27B GGUF?
It depends on the quant: file is 0.0 GB, Q2_K is 10.9 GB, Q3_K_S is 12.3 GB, IQ3_S is 12.6 GB, IQ3_M is 12.8 GB, Q3_K_M is 13.5 GB and 9 more.
What context length does DiscoveryRSI 27B 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 DiscoveryRSI 27B GGUF?
The files are on Hugging Face in the mradermacher/DiscoveryRSI-27B-i1-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 DiscoveryRSI 27B 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 DiscoveryRSI 27B on 8 GB VRAM?
No. The smallest quant requires 13.5GB of VRAM at 8k context, which exceeds an 8GB GPU.
What license applies to this model?
The model is released under the Apache‑2.0 license.
Does this model support vision tasks?
No, DiscoveryRSI 27B is a text‑only model.