estimate

Can I run Kolibri-1 on an RTX 5090?

No: needs ~50.8 GB, this card has ~31.4 GB usable (estimate)

speed: not estimated for MoE yet

Can I run Kolibri-1 on an RTX 5090? No: needs ~50.8 GB, this card has ~31.4 GB usable (estimate). About 50.8 GB at Q4_K_M (estimate).

VRAM per quant for Kolibri-1

Updated . The later of the hardware price date and the formula date.

Kolibri-1 on RTX 5090, formula estimate
QuantContextWeightsKVOverheadTotalUsableFit
Q4 Q4_K_M8,192 tokens49.8 GB measured GGUF file size0.2 GB estimate0.8 GB estimate50.8 GB estimate31.4 GB estimateno
Q5 Q5 (~0.71 bytes/param)8,192 tokens55.5 GB estimate0.2 GB estimate0.8 GB estimate56.5 GB estimate31.4 GB estimateno
Q8 Q88,192 tokens83.6 GB estimate0.2 GB estimate0.8 GB estimate84.6 GB estimate31.4 GB estimateno
FP16 FP168,192 tokens156.2 GB estimate0.2 GB estimate0.8 GB estimate157.2 GB estimate31.4 GB estimateno
Q4, longer context32,768 tokens49.8 GB measured GGUF file size0.7 GB estimate0.8 GB estimate51.3 GB estimate31.4 GB estimateno

Formula estimate, not a benchmark. Method →

Cheapest catalog option that fits at Q4

Mac mini M4 Pro 64GB, catalog price, €1,890, dated 2026-10-16. No buy link.

This hardware

$7,052€6,299

new (lowest in-stock EU)

price as of 16 Oct 2026

PriceSquirrel

Cheapest in-stock listing on 16 Oct 2026: €6,299, ASUS ROG Astral GeForce RTX 5090 32GB OC White at Proshop (FI). MSI Gaming Trio OC at Compumsa (BE) was €6,571 and out of stock. A 16 Oct 2026 fact-check notes BE/NL/DE about €7,900–€8,800. No used median was recorded. NVIDIA (Jeff Fisher, 16 Oct 2026) denies a production halt; supply is tight and some retailers have delisted the card.

Embed this

Kolibri-1 on RTX 5090

[![Kolibri-1 Q4 on RTX 5090: ✗ · needs 50.8 GB (estimate)](https://localllmrig.com/badge/kolibri-1/rtx-5090.svg)](https://localllmrig.com/can-i-run/kolibri-1/rtx-5090?utm_source=badge)

Questions

Can I run Kolibri-1 on an RTX 5090?
No: needs ~50.8 GB, this card has ~31.4 GB usable (estimate).
How much memory does Kolibri-1 need at Q4?
About 50.8 GB at 8,192 tokens (estimate): 49.8 GB weights (measured GGUF file size), 0.2 GB KV cache, 0.8 GB overhead.
How fast is Kolibri-1 on RTX 5090 (estimate)?
speed: not estimated for MoE yet

Rig Report waitlist

A written hardware plan for one model and budget. Planned price, not for sale yet.

Sign up with consent and download GPU Buying Cheat Sheet (EU, Oct 2026). The file is not emailed.

Read next: Building a local LLM rig in the RAMageddon.

Notify me

These offers are not for sale. Leave your email and we will write when one opens. Nothing is charged.

What the Rig Report is

Can I run Kolibri-1 on an RTX 5090? VRAM & speed (estimate) · localLLMrig