localLLMrig
Menu

Which GPUs and Macs run Kimi K3.1 Pro?

Key facts

Not on the cards on this page: Kimi K3.1 Pro needs about 1681 GB of memory, more than any of them has.

About 1,680.8 GB at Q4 before conversation memory, our estimate. Checked . model card.

None of the 43 graphics cards, PCs and Macs on our list holds the whole model at the standard quality in its graphics memory.

For this model we could not count the memory a conversation takes, so real use needs more than shown here.

Find hardware for Kimi K3.1 ProAbout this model

LIVE IN BROWSER · $0 · NO LOGIN

Test 10 open LLMs free in your browser before the Kimi K3.1 Pro weights on 4 Nov

Open full 8-model playground ↗

Before the open weights for Kimi K3.1 Pro land on 4 November 2026 (2.8T sparse mixture of experts; a flat 4-bit file is about 1.4 TB, a multi-node cluster), you can test 10 open LLMs free in your browser at https://localllmrig.com/ with no login and 0 GB of local VRAM. The prompts below run Recursive Flint and Gemma 4 31B. Kimi K3.1 Pro is already on the pass at $2 per million input tokens and $10 per million output tokens, so trying it in the chat needs a pass.

Test 10 open LLMs free in your browser →https://localllmrig.com/can-i-run/kimi-k3.1-pro

Click a starter prompt below or type your own question to watch Recursive Flint stream side by side against Gemma 4 31B right on this page:

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.

Which graphics cards run it

Seven popular graphics cards and two PCs with two cards each, at the standard quality (Q4). Click one for the full answer: memory, speed and price.

Doesn't fit10

Not enough graphics memory: it needs about 1,680.8 GB.

Every model on every card

Which Macs and mini PCs run it

Macs and mini PCs from the picker, at the standard quality (Q4). A Mac shares its memory with the rest of the computer. Each name opens that machine's page.

Doesn't fit12

Not enough shared memory: it needs about 1,680.8 GB.

Cheapest hardware for each size

From all 43 graphics cards, PCs and Macs on our list. "Runs slowly" means part of the model runs from normal memory: cheaper, but much slower. A smaller download needs less memory and answers a little less well.

  • Standard quality (Q4)No machine on our list runs this size.
  • Standard quality (Q4), runs slowlyNo machine on our list runs this size.

Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.

Prices moved: see Building a local LLM rig in the RAMageddon.

About Kimi K3.1 Pro

2800B parameters. Parameter count is an estimate. More parameters usually means a smarter model that needs more memory.

Licence:
Not published yet source
Longest conversation:
about 1573 pages of text (1,048,576 tokens)
Input:
text+image+video in, text out
Released:
source
Sources and method

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/.

Parameter source · Model page

Memory at each quality level

Each download of Kimi K3.1 Pro is a different size. The total adds the file, the memory a conversation of about 12 pages of text (8,192 tokens) takes, and 0.8 GB of working space. A measured file size is labelled; the rest is our estimate. The last column is the cheapest machine that holds the total.

Swipe the table sideways to see every column, up to the cheapest machine.

Memory per quant for Kimi K3.1 Pro
Quality (file)File sizeConversationWorking spaceTotalCheapest machine that holds it
Q82,996.0 GB0.0 GBnot counted0.8 GB2,996.8 GBNo machine on our list runs this size.
Q41,680.0 GB0.0 GBnot counted0.8 GB1,680.8 GBNo machine on our list runs this size.

speed: not estimated for MoE yet.

Our estimate leaves out the conversation memory for this model: real use needs more than the figures shown.

Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate

Questions

Can I run Kimi K3.1 Pro on 24GB?
Not in full. Kimi K3.1 Pro needs about 1,680.8 GB at the standard quality, and a 24 GB card leaves about 23.4 GB usable. Conversation memory is not counted for this model, so real use needs more.
Can I run Kimi K3.1 Pro on a 128GB Mac?
No, by our estimate. Kimi K3.1 Pro needs about 1,680.8 GB, and Mac Studio M4 Max 128GB and Mac Studio M5 Max 128GB leave about 96.0 GB usable of 128 GB. Conversation memory is not counted for this model, so real use needs more.
How fast is Kimi K3.1 Pro on an RTX 5090?
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.