estimate
Can I run Kolibri-1 on a Dual RTX 3090?
Only with CPU offload (slow) (estimate). A smaller quant such as IQ4_XS (~43.6 GB file) fits fully.
speed: not estimated for MoE yet
Can I run Kolibri-1 on a Dual RTX 3090? Only with CPU offload (slow) (estimate). A smaller quant such as IQ4_XS (~43.6 GB file) fits fully.. About 50.8 GB at Q4_K_M (estimate).
Updated . The later of the hardware price date and the formula date.
| Quant | Context | Weights | KV | Overhead | Total | Usable | Fit |
|---|---|---|---|---|---|---|---|
| Q4 Q4_K_M | 8,192 tokens | 49.8 GB measured GGUF file size | 0.2 GB estimate | 0.8 GB estimate | 50.8 GB estimate | 46.8 GB estimate | offload |
| Q5 Q5 (~0.71 bytes/param) | 8,192 tokens | 55.5 GB estimate | 0.2 GB estimate | 0.8 GB estimate | 56.5 GB estimate | 46.8 GB estimate | offload |
| Q8 Q8 | 8,192 tokens | 83.6 GB estimate | 0.2 GB estimate | 0.8 GB estimate | 84.6 GB estimate | 46.8 GB estimate | offload |
| FP16 FP16 | 8,192 tokens | 156.2 GB estimate | 0.2 GB estimate | 0.8 GB estimate | 157.2 GB estimate | 46.8 GB estimate | offload |
| Q4, longer context | 32,768 tokens | 49.8 GB measured GGUF file size | 0.7 GB estimate | 0.8 GB estimate | 51.3 GB estimate | 46.8 GB estimate | offload |
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
$6,054€5,408
price as of 16 Oct 2026
128 GB DDR4 (estimate): $2,754€2,460. From the 16 Oct 2026 fact-check.
rest of system (estimate): $560€500. The total is the GPU price plus the RAM line plus this estimate. It is not a checked system price.
price unverifiedGPU line is 2× the used median €1,224 (€2,448), labelled used, from pcprice.watch (https://www.pcprice.watch/gpu-buying-guide/rtx-3090-price-used-and-specs). 128 GB DDR4 (estimate) €2,460, from the 16 Oct 2026 fact-check. Rest of system (estimate) €500. Other parts from €500 in that fact-check. Not a shop listing. The total is the GPU price plus the RAM line plus that rest estimate. It is not a checked system price.
Embed this
Kolibri-1 on Dual RTX 3090
[](https://localllmrig.com/can-i-run/kolibri-1/dual-rtx-3090?utm_source=badge)
Questions
- Can I run Kolibri-1 on a Dual RTX 3090?
- Only with CPU offload (slow) (estimate). A smaller quant such as IQ4_XS (~43.6 GB file) fits fully..
- 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 Dual RTX 3090 (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.