Smaller alternatives
Models that need less memory than Kimi K3 and score about as well or better.
Kimi K3
MoEVision
Moonshot AI · 2.8T (104B active) · Mixture of experts
Kimi K3 is a 2.8T model from Moonshot AI with a 1M-token context. At Q4_K_M with an 8K context it needs about 1,584.5 GB; 1982 GB leaves room for longer chats.
Mixture of experts
Parameters: 2.8T · Active: 104B
All 2.8T parameters load into memory, but only 104B 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 | 0.1 GB | 1,584.4 GB |
| 8K | 0.2 GB | 1,584.5 GB |
| 32K | 0.8 GB | 1,585.1 GB |
| 128K | 3.4 GB | 1,587.6 GB |
| 256K | 6.8 GB | 1,591 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 Kimi K3 grade A or S at Q4_K_M.
No desktop device in our catalog runs it at grade A or better.
Can I run Kimi K3 locally?
Can I run Kimi K3 locally?
Yes, if your GPU or Mac has about 1,584.5 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 Kimi K3 need?
About 1,584.5 GB at Q4_K_M with an 8K context and 2,751.6 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.