Kimi K3 2.8T — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated August 15, 2026

Model library → Kimi K3 → Kimi K3 2.8T

The full 2.8-trillion-parameter Kimi K3 MoE, activating 104B parameters per token by selecting 16 of 896 experts. Moonshot's largest and most capable model, positioned above Kimi K2.6 on agentic coding and long-horizon reasoning at release. Native text + vision with a 1M-token context. Weights went public on 26–27 July 2026 under the bespoke Kimi K3 License — open-weight, but not an OSI-approved open-source license, so check the commercial threshold before deploying. Self-hosting requires ~1.4 TB of memory at Q4, so in practice this is an API model — as is every Kimi K2.x release, which are all 1T-class MoE models despite their 32B active-parameter figure.

Kimi K3 2.8T needs about 1691 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters2.8 Trillion (104B active)
Context window1,000,000
ArchitectureMixture-of-Experts (896 experts, 16 active) + Vision
ProviderMoonshot AI
LicenceKimi K3 License (open-weight, not OSI open-source)
Specified atQ4_K_M
System RAM2048 GB
Record updated2026-08-15

Licence

Kimi Open-Weight — commercial use permitted. Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K920.5 GB921.3 GB—Won't fit
Q3_K_M1193.5 GB1194.3 GB—Won't fit
Q4_K_M1690.5 GB1691.3 GB—Won't fit
Q5_K_M1984.5 GB1985.3 GB—Won't fit
Q6_K2296.0 GB2296.8 GB—Won't fit
Q8_02975.0 GB2975.8 GB—Won't fit
F165600.0 GB5600.8 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the Kimi K3 2.8T VRAM calculator.

Deploy in the Cloud NowRunPod

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

How to Run Kimi K3 2.8T

Install Ollama, then run:

ollama run kimi-k3

Weights on Hugging Face: moonshotai/Kimi-K3.

Best for: agentic tasks, coding, software engineering, reasoning, cloud api.

Can I Run Kimi K3 2.8T on My GPU?

Kimi K3 2.8T — Frequently Asked Questions

How much VRAM does Kimi K3 2.8T need?
About 1691 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Kimi K3 2.8T run on an RTX 4090 (24 GB)?
No. Kimi K3 2.8T needs about 1691 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Kimi K3 2.8T locally?
Install Ollama and run `ollama run kimi-k3`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

← All Kimi K3 models | VRAM calculator | Check your own hardware