What hardware do you need to run Ornith 1.5 122B?

Ornith 1.5 122B at Q4_K_M is 76 GB of weights, with a context ceiling of 256k tokens. Ornith's MIT-licensed coding and agent model, a post-train of Qwen3.5 122B-A10B: 125B total with 10B of it active for every token, so a token reads a fraction of the 76 GB on disk. It reads images as well as text, and the vision projector is a separate 0.91 GB download this page does not price. On the cheapest machine that runs it, a Framework Desktop, 128GB, it generates 21 tok/s at 32k of context, worked out from memory bandwidth.

How good is Ornith 1.5 122B, really?

It has not been placed on the intelligence index yet. See the whole table.

What Ornith 1.5 122B costs either way

Nobody rents Ornith 1.5 122B by the token. The closest hosted match, Qwen3.5 122B-A10B, costs $0.26 per million input tokens and $2.08 per million output (OpenRouter, cheapest active endpoint, checked 2026-10-26). Buying a machine only beats that if you use it hard enough, for long enough, that the hardware price divides down below the rental bill. What a million tokens costs each way puts the two prices side by side.

Machines that run Ornith 1.5 122B

Every machine here holds it to 256k, which is this model's own ceiling and the longest the calculator offers, so the choice between them is speed and price rather than how much you can keep in the window.

The table is the cheapest machine in each family, not the only one that runs it: 17 of the 56 machines on this site hold it at 32k. Within a family only memory decides, so that is every NVIDIA card with 96GB or more, every Mac Studio, Strix Halo box and MacBook Pro with 128GB or more and the DGX Spark, 128GB. One table sets every machine against the others: price, the memory its GPU can use, what it holds and how long it takes to pay for itself.

One machine per family, cheapest first. Speeds are measured where a public benchmark exists and estimated from memory bandwidth otherwise; the calculator says which for any configuration. The longest context is the longest setting the calculator offers that the machine still holds this model at, cache included, and no machine is shown taking it past its own 256k limit. Each one opens the calculator on that machine at that length.

For scale, the calculator starts from 80 tok/s for a hosted API and times a local machine against it. 1 of the 5 above reaches it, and the slowest is 21 tok/s.

The cheapest machine that runs it is sold with 128 GB. There is a page on what 128 GB runs, machine by machine: it names the 11 machines here sold at that size, and the 38 current models the roomiest of them holds at 32k, this one among them.

It fits in less memory than that: the smallest size here that runs it at 32k is 96 GB, on the RTX PRO 6000 Blackwell, 96GB at $18,000, card only, which hands a model 95 GB.

Run Ornith 1.5 122B at 256k on the Strix Halo Framework Desktop, 128GB

How much memory does Ornith 1.5 122B need at 256k?

Every figure above is priced at 32k of context. At 256k, which is this model's own ceiling and the longest the calculator offers, Ornith 1.5 122B needs 82.3 GB rather than 76.6 GB. The weights are the same either way; the key-value cache goes from 0.8 GB to 6.4 GB.

The window costs nothing in hardware: the same 12 of the 37 machines here still sold at a published price hold Ornith 1.5 122B at both lengths, and the cheapest of them is the Framework Desktop, 128GB at $3,449.

On the Framework Desktop, 128GB it runs 21 tok/s estimated at 32k and 11 tok/s estimated at 256k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

The specifics

Parameters

125.1B, of which 10B are active per token

Quantisation

Q4_K_M

Weights on disk

76 GB

KV cache

0.8 GB at 32k context — Thirty-six of the 48 layers use linear attention and keep a fixed state whatever the context; the other 12 cache every token, so the whole 256k window costs about 6.4 GB. The shape is Qwen3.5 122B-A10B's exactly, down to the parameter count. Ornith's own four-bit GGUF is the one priced, at 75.84 GB; unsloth's dynamic UD-Q4_K_XL of the same weights is 79.71 GB. How weights and cache add up.

Maximum context

256k tokens (up to 1M with YaRN)

Licence

MIT

Sources

ornith-ai/Ornith-1.5-122B, ornith-ai/Ornith-1.5-122B-GGUF