estimate
Can I run Ornith-1.5-122B on an RTX 5090?
No: needs ~76.8 GB, this card has ~31.4 GB usable (estimate)
speed: not estimated for MoE yet
Can I run Ornith-1.5-122B on an RTX 5090? No: needs ~76.8 GB, this card has ~31.4 GB usable (estimate). About 76.8 GB at Q4_K_M (estimate).
VRAM per quant for Ornith-1.5-122B
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 | 75.8 GB measured GGUF file size | 0.2 GB estimate | 0.8 GB estimate | 76.8 GB estimate | 31.4 GB estimate | no |
| Q5 Q5 (~0.71 bytes/param) | 8,192 tokens | 88.8 GB estimate | 0.2 GB estimate | 0.8 GB estimate | 89.8 GB estimate | 31.4 GB estimate | no |
| Q8 Q8 | 8,192 tokens | 133.8 GB estimate | 0.2 GB estimate | 0.8 GB estimate | 134.8 GB estimate | 31.4 GB estimate | no |
| FP16 FP16 | 8,192 tokens | 250.2 GB estimate | 0.2 GB estimate | 0.8 GB estimate | 251.2 GB estimate | 31.4 GB estimate | no |
| Q4, longer context | 32,768 tokens | 75.8 GB measured GGUF file size | 0.8 GB estimate | 0.8 GB estimate | 77.4 GB estimate | 31.4 GB estimate | no |
Formula estimate, not a benchmark. Method →
Cheapest catalog option that fits at Q4
Mac Studio M4 Max 128GB, catalog price, €3,290, dated 2026-10-16. No buy link.
This hardware
$7,725€6,900
new (lowest in-stock EU)
price as of 20 Oct 2026
PriceSquirrelCheapest in-stock listing on 20 Oct 2026: €6,900, Gigabyte AORUS XTREME WATERFORCE 32G at Joybuy (FR), via PriceSquirrel. The cheapest listing overall, €6,788 at Compumsa (BE), was out of stock. 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
Ornith-1.5-122B on RTX 5090
[](https://localllmrig.com/can-i-run/ornith-1.5-122b/rtx-5090?utm_source=badge)
Questions
- Can I run Ornith-1.5-122B on an RTX 5090?
- No: needs ~76.8 GB, this card has ~31.4 GB usable (estimate).
- How much memory does Ornith-1.5-122B need at Q4?
- About 76.8 GB at 8,192 tokens (estimate): 75.8 GB weights (measured GGUF file size), 0.2 GB KV cache, 0.8 GB overhead.
- How fast is Ornith-1.5-122B 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.