Small DS R1 needs about 134.4 GB of memory at Q4_K_M (a 133.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.3 GB to 181.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.
Small DS R1 is a 221B-parameter Small model in GGUF format, quantized by mradermacher. Its trained context length is 160K tokens. The repository has 24 quant files, from 0.3 GB to 181.5 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 1.2 GB | Fits | Get file → | |
| IQ1_S | 44.6 GB | 45.5 GB | Too big | Get file → | |
| IQ1_M | 49.6 GB | 50.5 GB | Too big | Get file → | |
| IQ2_XXS | 57.9 GB | 58.8 GB | Too big | Get file → | |
| IQ2_XS | 64.6 GB | 65.5 GB | Too big | Get file → | |
| IQ2_S | 65.5 GB | 66.3 GB | Too big | Get file → | |
| IQ2_M | 72.1 GB | 73.0 GB | Too big | Get file → | |
| Q2_K_S | 74.1 GB | 74.9 GB | Too big | Get file → | |
| Q2_K | 80.7 GB | 81.6 GB | Too big | Get file → | |
| IQ3_XXS | 85.2 GB | 86.1 GB | Too big | Get file → | |
| IQ3_XS | 90.2 GB | 91.1 GB | Too big | Get file → | |
| IQ3_S | 95.5 GB | 96.4 GB | Too big | Get file → | |
| Q3_K_S | 95.5 GB | 96.4 GB | Too big | Get file → | |
| IQ3_M | 96.3 GB | 97.2 GB | Too big | Get file → | |
| Q3_K_M | 105.4 GB | 106.2 GB | Too big | Get file → | |
| Q3_K_L | 114.6 GB | 115.5 GB | Too big | Get file → | |
| IQ4_XS | 117.8 GB | 118.7 GB | Too big | Get file → | |
| Q4_0 | 125.0 GB | 125.8 GB | Too big | Get file → | |
| Q4_K_S | 125.2 GB | 126.1 GB | Too big | Get file → | |
| Q4_K_M | 133.5 GB | 134.4 GB | Too big | Get file → | |
| Q4_1 | 138.5 GB | 139.3 GB | Too big | Get file → | |
| Q5_K_S | 152.2 GB | 153.1 GB | Too big | Get file → | |
| Q5_K_M | 156.8 GB | 157.6 GB | Too big | Get file → | |
| Q6_K | 181.5 GB | 182.4 GB | Too big | Get file → |
What GPU do you need for Small DS R1?
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 (0.3 GB file, about 1.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.2 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.2 GB in use).
- 48 GB VRAM: the best quant that fits is IQ1_S (44.6 GB file, about 45.5 GB in use).
Which Small DS R1 quant should you choose?
Q4_K_M is the usual starting point for Small DS R1: it balances file size and quality well. Here it is a 133.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.3 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 Small DS R1
How much VRAM does Small DS R1 need?
About 134.4 GB at Q4_K_M with an 8K context window. That is the 133.5 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 Small DS R1 on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Small DS R1 GGUF?
It depends on the quant: file is 0.3 GB, IQ1_S is 44.6 GB, IQ1_M is 49.6 GB, IQ2_XXS is 57.9 GB, IQ2_XS is 64.6 GB, IQ2_S is 65.5 GB and 18 more.
What context length does Small DS R1 support?
The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.4 GB at 32K.
Where can I download Small DS R1 GGUF?
The files are on Hugging Face in the mradermacher/Small-DS-R1-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.