Olmo-3.1-32B-Think - DASH-Q 2-bit GGUF
llama.cpp GGUF files of allenai/Olmo-3.1-32B-Think quantized with DASH-Q, at several 2-bit-class sizes. Every file uses only standard llama.cpp tensor types (no tensor above 4 bits) and loads in any recent llama.cpp build.
| File | Type | Size | Bits / weight |
|---|---|---|---|
Olmo-3.1-32B-Think-DASHQ-IQ2_XXS.gguf |
IQ2_XXS | 8.92 GB | 2.21 |
Olmo-3.1-32B-Think-DASHQ-IQ2_XS.gguf |
IQ2_XS | 10.22 GB | 2.53 |
Olmo-3.1-32B-Think-DASHQ-IQ2_M.gguf |
IQ2_M | 11.05 GB | 2.74 |
Olmo-3.1-32B-Think-DASHQ-Q2_K_XL.gguf |
Q2_K_XL | 12.22 GB | 3.03 |
Perplexity (lower is better)
| Type | Model | Size | WikiText-2 | C4 |
|---|---|---|---|---|
| IQ2_XXS | llama.cpp IQ2_XXS (imatrix) | 8.76 GB | 8.41 | 15.96 |
| IQ2_XXS | unsloth UD-IQ2_XXS | 8.91 GB | 8.47 | 16.02 |
| IQ2_XXS | DASH-Q IQ2_XXS | 8.92 GB | 7.99 | 15.69 |
| IQ2_XS | llama.cpp IQ2_XS (imatrix) | 9.69 GB | 7.84 | 15.38 |
| IQ2_XS | DASH-Q IQ2_XS | 10.22 GB | 7.29 | 14.59 |
| IQ2_M | llama.cpp IQ2_M (imatrix) | 10.97 GB | 7.28 | 14.53 |
| IQ2_M | unsloth UD-IQ2_M | 11.05 GB | 7.42 | 14.79 |
| IQ2_M | DASH-Q IQ2_M | 11.05 GB | 6.99 | 14.24 |
| Q2_K_XL | llama.cpp Q2_K (imatrix) | 12.01 GB | 7.30 | 14.65 |
| Q2_K_XL | unsloth UD-Q2_K_XL | 12.33 GB | 7.35 | 14.71 |
| Q2_K_XL | DASH-Q Q2_K_XL | 12.22 GB | 6.92 | 14.16 |
llama-perplexity, context 2048; WikiText-2 test, C4 validation (256 x 2048 tokens).
Usage
llama-cli -m Olmo-3.1-32B-Think-DASHQ-Q2_K_XL.gguf -ngl 99 -c 8192
License
Inherits the license of the base model (allenai/Olmo-3.1-32B-Think).