Cheapest way to run Ornith-1.5-122B
We earn commissions when you shop through the links below.
Ornith-1.5-122B needs 79.9 GB at 4-bit — cheapest rental $1.69/hr.
Quick answer
At 4-bit with an 8K-token conversation, Ornith-1.5-122B needs about 79.9 GB. The cheapest rental big enough is RTX Pro 6000 on Runpod at $1.69 an hour.
| Option | What you need | Cost | Notes |
|---|---|---|---|
| Your own GPU | Doesn't fit any single consumer card in our list (largest 32 GB) at 4-bit with 8K context | – | – |
| Mac (unified memory) | Mac, 96 GB at 4-bit (Q4_K_M), needs 79.9 GB | No Mac prices in our data | $0 per token once you own it |
| Rent a GPU | RTX Pro 6000 (96 GB total) on Runpod Referral link, Community Cloud | $1.69 per hour | Pay only while it runs. Price checked 2026-11-09 |
Fit rule: the Q4_K_M file (or the highest precision that fits) plus an 8K-token FP16 KV cache under 90% of memory, same as the calculator. Sizes and sources: Ornith-1.5-122B VRAM page. Rental prices: GPU prices (checked 2026-11-09). Hourly and per-token prices measure different things, so which is cheaper depends on how much you use it.
Links marked Referral link, Affiliate partner or Amazon affiliate link may earn us credit or a commission at no cost to you. Disclosure.
Precision ladder: what each quant costs
| Precision | Needs at 8K | Smallest consumer GPU | Smallest Mac | Cheapest single-GPU rental | Cheapest rental overall (any GPU count) |
|---|---|---|---|---|---|
| 16-bit (FP16/BF16) | 249.6 GB | none (max 32 GB) | Mac Studio, 512 GB at 16-bit (FP16/BF16) | B300 (288 GB) on Runpod, $6.94/hr | B300 (288 GB) on Runpod, $6.94/hr |
| 8-bit (Q8_0) | 132.8 GB | none (max 32 GB) | Mac Studio, 256 GB at 8-bit (Q8_0) | B200 (180 GB) on Runpod, $5.98/hr | 4× RTX A6000 (192 GB) on Lambda, $4.36/hr |
| 4-bit (Q4_K_M) | 79.9 GB | none (max 32 GB) | Mac, 96 GB at 4-bit (Q4_K_M) | RTX Pro 6000 (96 GB) on Runpod, $1.69/hr | RTX Pro 6000 (96 GB) on Runpod, $1.69/hr |
Every row names its precision, Mac rows included (Macs share unified memory with the system, so the same 90% rule applies). Single-GPU and multi-GPU rentals are listed separately: a multi-GPU rental needs software that splits the model across cards (llama.cpp, vLLM tensor parallel). Prices checked 2026-11-09.
How context length changes the bill (4-bit)
| Context | Needs | Cheapest rental overall |
|---|---|---|
| 8K tokens | 79.9 GB | RTX Pro 6000 (96 GB) on Runpod, $1.69/hr |
| 32K tokens | 80.5 GB | RTX Pro 6000 (96 GB) on Runpod, $1.69/hr |
| 128K tokens | 82.9 GB | RTX Pro 6000 (96 GB) on Runpod, $1.69/hr |
What $100 of rental buys you
We list no GPU purchase prices (they change daily and we cannot check them), so this page does not compare renting with buying. At the cheapest rental that fits (RTX Pro 6000 (96 GB) on Runpod, $1.69/hr), $100 of rental buys about 59 hours of running Ornith-1.5-122B at 4-bit with 8K context. Electricity, storage and setup time are not counted.
Fit quirks for this model
- Only the 12 full-attention layers grow with context: 12 × 2 KV heads × 256 head dim × 2 × 2 bytes. The 36 linear-attention layers keep a fixed-size state that is not included.
- No Q4_K_M build in the Unsloth repo; the 4-bit column is Unsloth UD-Q4_K_XL (3 files). Ollama's ornith-1.5:122b-q4_K_M tag is 77 GB.
- Maximum context is 262,144 tokens; longer settings are capped.
Model data checked 2026-10-25; rental prices checked 2026-11-09. For file sizes, sources and the full fit table see the Ornith-1.5-122B VRAM requirements page; this page is only about cost.
Get fit alerts for your GPU
Join the fit-alerts waitlist
Alerts are not running yet. Join the waitlist and pick your card once; when alerts launch we will email you once to confirm, and only after you confirm will you get the first alerts. Unsubscribe any time.
More: all cheapest-way pages · cheapest GPU rental by VRAM · Ask VRAMNeeded · Scan my GPU