Smaller alternatives
Models that need less memory than Inkling Small and score about as well or better.
Inkling Small
MoEVisionTThinking Machines Lab · 266B (12B active) · Mixture of experts
Inkling Small is a 266B model from Thinking Machines Lab with a 1M-token context. At Q4_K_M with an 8K context it needs about 149 GB; 188 GB leaves room for longer chats.
Mixture of experts
Parameters: 266B · Active: 12B
All 266B parameters load into memory, but only 12B work on each token, so it runs at the speed of a much smaller model.
Quantization options
| Quant | Bits | Memory | Quality | On your hardware |
|---|---|---|---|---|
| Q2_K | 3.16 | — | Noticeably worse | … |
| Q3_K_M | 4 | — | Some loss | … |
| Q4_K_M | 4.89 | — | Good | … |
| Q5_K_M | 5.7 | — | Good | … |
| Q6_K | 6.56 | — | Near original | … |
| Q8_0 | 8.5 | — | Near original | … |
| F16 | 16 | — | Original | … |
Memory by context length
At Q4_K_M. The context cache grows with every token the model keeps in mind.
| Context | Context cache | Total |
|---|---|---|
| 4K | 0.2 GB | 148.9 GB |
| 8K | 0.3 GB | 149 GB |
| 32K | 0.9 GB | 149.6 GB |
| 128K | 3.6 GB | 152.3 GB |
| 256K | 7.1 GB | 155.8 GB |
Next steps
Compare it with
Scored models of a similar size, side by side on your device.
Least hardware that runs it well
Desktop devices with the least memory that give Inkling Small grade A or S at Q4_K_M.
Can I run Inkling Small locally?
Can I run Inkling Small locally?
Yes, if your GPU or Mac has about 149 GB free for it at Q4_K_M. Open this page on that computer to see the grade for your exact hardware, then start it with llama.cpp, Ollama or LM Studio.
How much memory does Inkling Small need?
About 149 GB at Q4_K_M with an 8K context and 261.6 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.