Will this model run on your hardware?
Can I run Thinking Machines: Inkling Small locally?
- 266B parameters (19B active, MoE)
- licence: apache-2.0
- Weights: thinkingmachines/Inkling-Small · GGUF: unsloth/Inkling-Small-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 280.3 GB |
| UD-Q6_K | 218.9 GB |
| UD-Q5_K_M | 196.1 GB |
| UD-Q4_K_M | 162.5 GB |
| MXFP4 | 158.0 GB |
| UD-Q3_K_M | 119.4 GB |
Run it locally
ollama run hf.co/unsloth/Inkling-Small-GGUF:UD-Q4_K_M
llama serve -hf unsloth/Inkling-Small-GGUF:UD-Q4_K_M
LM Studio: open unsloth/Inkling-Small-GGUF