Kimi K2.6
Kimi K2.6 by Moonshot AI (1000B parameters, MoE with 32B active per token). At Q4_K_M with an 8K context it needs about 593.9 GiB of memory. Moonshot's 1-trillion-parameter MoE (32B active): server-class, too big for any single machine in our catalog even at 4-bit. Ollama only offers it as a cloud model.
Last updated: 2026-10-13
Model facts
Memory needed
Weights + KV cache + runtime overhead, in GiB. Lower quantization = less memory, slightly lower quality.
| Quantization | 4K context | 8K context | 32K context |
|---|---|---|---|
| Q4_K_M | 593.6 GiB | 593.9 GiB | 595.5 GiB |
| Q5_K_M | 696.3 GiB | 696.6 GiB | 698.2 GiB |
| Q6_K | 806.3 GiB | 806.6 GiB | 808.2 GiB |
| Q8_0 | 1039.8 GiB | 1040.0 GiB | 1041.7 GiB |
| FP16 | 1956.5 GiB | 1956.8 GiB | 1958.4 GiB |
Which hardware runs it
Best quantization that fits each device with a 8K context. Estimates, not benchmarks. See the methodology.
Frequently asked questions
How much VRAM does Kimi K2.6 need?
With an 8K context, about 593.9 GiB at Q4_K_M and 1040.0 GiB at Q8_0 (weights + KV cache + runtime overhead). Longer contexts need more memory for the KV cache.
Can Kimi K2.6 run on an GeForce RTX 4090?
Kimi K2.6 does not fit on the GeForce RTX 4090 (24 GB), even at Q4_K_M with an 8K context.
Can I run Kimi K2.6 on a Mac?
Kimi K2.6 does not fit on the M3 Ultra (512 GB), even at Q4_K_M with an 8K context.
Can Kimi K2.6 be used commercially?
Kimi K2.6 is released under Modified MIT. The licence allows commercial use (read its conditions).