# Kimi K2.6

> OnPrem World · https://onpremworld.com/en/models/kimi-k2.6 · Last updated: 2026-10-14 · CC BY 4.0

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.

|  |  |
|---|---|
| Developer | Moonshot AI |
| Parameters | 1000B (32B active, MoE) |
| Native context | 262,144 tokens |
| Licence | Modified MIT |
| Commercial use | Yes |
| KV cache | Compressed latent KV (MLA), 61 layers |
| Released | 2026-04 |

## Memory needed

Weights + KV cache + runtime overhead, in GiB. Lower quantization = less memory, slightly lower quality.

| Quantization | 4K | 8K | 32K |
|---|---|---|---|
| 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 (8K)

| Hardware | Memory | Best quant | tok/s (est.) |
|---|---|---|---|
| GeForce RTX 3060 (12 GB) | 12 GB | Doesn't fit | – |
| GeForce RTX 3090 | 24 GB | Doesn't fit | – |
| GeForce RTX 4060 Ti 16GB | 16 GB | Doesn't fit | – |
| GeForce RTX 4080 SUPER | 16 GB | Doesn't fit | – |
| GeForce RTX 4090 | 24 GB | Doesn't fit | – |
| GeForce RTX 5060 Ti 16GB | 16 GB | Doesn't fit | – |
| GeForce RTX 5070 | 12 GB | Doesn't fit | – |
| GeForce RTX 5070 Ti | 16 GB | Doesn't fit | – |
| GeForce RTX 5080 | 16 GB | Doesn't fit | – |
| GeForce RTX 5090 | 32 GB | Doesn't fit | – |
| Radeon RX 7900 XT | 20 GB | Doesn't fit | – |
| Radeon RX 7900 XTX | 24 GB | Doesn't fit | – |
| Radeon RX 9060 XT 16GB | 16 GB | Doesn't fit | – |
| Radeon RX 9070 XT | 16 GB | Doesn't fit | – |
| Arc B580 | 12 GB | Doesn't fit | – |
| RTX A6000 | 48 GB | Doesn't fit | – |
| RTX 6000 Ada Generation | 48 GB | Doesn't fit | – |
| RTX PRO 5000 72GB Blackwell | 72 GB | Doesn't fit | – |
| RTX PRO 6000 Blackwell Workstation Edition | 96 GB | Doesn't fit | – |
| Radeon AI PRO R9700 | 32 GB | Doesn't fit | – |
| Arc Pro B60 | 24 GB | Doesn't fit | – |
| Arc Pro B70 | 32 GB | Doesn't fit | – |
| M4 Pro | 64 GB | Doesn't fit | – |
| M4 Max (14-core CPU / 32-core GPU) | 36 GB | Doesn't fit | – |
| M4 Max (16-core CPU / 40-core GPU) | 128 GB | Doesn't fit | – |
| M3 Ultra | 512 GB | Doesn't fit | – |
| M5 | 32 GB | Doesn't fit | – |
| M5 Pro | 64 GB | Doesn't fit | – |
| M5 Max (18-core CPU / 32-core GPU) | 36 GB | Doesn't fit | – |
| M5 Max (18-core CPU / 40-core GPU) | 128 GB | Doesn't fit | – |
| M5 Ultra | 512 GB | Doesn't fit | – |
| M6 (16GB configuration, 153 GB/s) | 16 GB | Doesn't fit | – |
| M6 (24GB/32GB configurations, 170 GB/s) | 32 GB | Doesn't fit | – |
| DGX Spark | 128 GB | Doesn't fit | – |
| RTX Spark (N1X) laptops & compact desktops | 128 GB | Doesn't fit | – |
| Ryzen AI Max+ 395 (Strix Halo) systems | 128 GB | Doesn't fit | – |
| Ryzen AI Max+ PRO 495 (Gorgon Halo) systems | 192 GB | Doesn't fit | – |

## 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).

## Sources

- https://datanorth.ai/news/moonshot-ai-releases-kimi-k2-6
- https://huggingface.co/moonshotai/Kimi-K2.6/blob/main/LICENSE
- https://huggingface.co/moonshotai/Kimi-K2.6
- https://huggingface.co/moonshotai/Kimi-K2.6/resolve/main/config.json