Can I run Kimi K3.1 Pro on a Dual RTX 3090?
Key facts
No: it needs about 1681 GB and this machine has 48 GB of graphics memory.
It needs about 1,680.8 GB at standard quality (estimate). Checked . model card.
For this model we could not count the memory a conversation takes, so real use needs more than shown here.
Updated · Kimi K3.1 Pro on every card
How much memory it needs
That is about 35.9 times what this machine has free.
Get a 1-line alert when a faster quant for Kimi K3.1 Pro drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new low-bit GGUF/MLX quant fits 128–256 GB rigs or when multi-GPU & Mac Studio prices drop >10% — weekly, zero spam.
What runs Kimi K3.1 Pro instead
Nothing among the 43 graphics cards, PCs and Macs on our list runs it fully.
See our picks for Kimi K3.1 Pro in Find hardware. Add your budget to see cheaper machines.
For comparison, a Dual RTX 3090 with 64 GB of normal memory (RAM) costs about $3,808€3,592. With 128 GB it gives the same answer and costs about $5,528€5,452. Machine details: Dual RTX 3090, 64 GB RAM, Dual RTX 3090, 128 GB RAM.
Kimi K3.1 Pro on other graphics cards
Doesn't fit10
Not enough graphics memory: it needs about 1,680.8 GB.
- RTX 3060 12GBhas 12 GB
- RTX 4060 Ti 16GBhas 16 GB
- RTX 3090has 24 GB
- RTX 4090has 24 GB
- RTX 5080has 16 GB
- RX 9060 XT 16GBhas 16 GB
- RTX 5090has 32 GB
- RX 7900 XTXhas 24 GB
- Dual RTX 3090has 48 GB
- Dual RTX 4090has 48 GB
More about the model itself, what it is good at and its licence: Kimi K3.1 Pro.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this machine.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Doesn't fit | 1,680.0 GB | 0.0 GBnot counted | 0.8 GB | 1,680.8 GB | 46.8 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Doesn't fit | 1,988.0 GB | 0.0 GBnot counted | 0.8 GB | 1,988.8 GB | 46.8 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Doesn't fit | 2,996.0 GB | 0.0 GBnot counted | 0.8 GB | 2,996.8 GB | 46.8 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Doesn't fit | 5,600.0 GB | 0.0 GBnot counted | 0.8 GB | 5,600.8 GB | 46.8 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Doesn't fit | 1,680.0 GB | 0.0 GBnot counted | 0.8 GB | 1,680.8 GB | 46.8 GB |
speed: not estimated for MoE yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Our estimate leaves out the conversation memory for this model: real use needs more than the figures shown.
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . model card.
Moonshot AI's sparse mixture of experts, stated as 2.8T total parameters, the same total class as Kimi K3. This row has no counted weight file and no config: on 26 Oct 2026 the OpenRouter models API listed no Hugging Face repo. A flat 4 bits per weight is 0.5 bytes per parameter, so 2.8T weights are 1,400 GB (1.4 TB). This site's Q4 estimate uses 0.60 bytes per parameter, 1,680.0 GB of weights plus 0.80 GB of working space (1,680.8 GB). Layer count, KV heads and the active-parameter count are not published, so conversation memory is not counted. Moonshot says the open-weight GGUF and FP8 checkpoints arrive on 4 November 2026. Until then the model is API-live as moonshotai/kimi-k3.1-pro. The default Moonshot endpoint is MXFP4 at $2 per million input tokens and $10 per million output tokens, and a cached input read is $0.20 per million. A file this size is a multi-node cluster. You can test it with a pass, or compare it with open models, at https://localllmrig.com/.
Questions
- Can I run Kimi K3.1 Pro on a Dual RTX 3090?
- No: it needs about 1681 GB and this machine has 48 GB of graphics memory.
- How much memory does Kimi K3.1 Pro need?
- About 1,680.8 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 1,680.0 GB for the model file (estimated), 0.0 GB to hold the conversation (not modelled for this model, so real use needs more) and 0.8 GB of working space.
- How fast is Kimi K3.1 Pro on a Dual RTX 3090?
- We don't give a speed for this model yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate