What hardware do you need to run Spark-X2.6 1.7B?

Spark-X2.6 1.7B at Q4_K_M is 1.1 GB of weights, with a context ceiling of 1M tokens. Dense 1.7B for on-device use, with a native million-token context, three thinking levels, English and Chinese. The 1.09 GB priced here is bartowski's four-bit, and mradermacher's comes to 1.11; XHToken's own file carries the same Q4_K_M label at 1.77 GB, because it keeps the 131,072-token embedding table at 16 bits and the output layer over it at 8, which is 0.82 GB of the download. On the cheapest machine that runs it, a Mac mini M6, 16GB, it generates 73 tok/s at 32k of context, worked out from memory bandwidth.

How good is Spark-X2.6 1.7B, really?

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

What Spark-X2.6 1.7B costs either way

Nobody rents Spark-X2.6 1.7B by the token. The closest hosted match, Granite 4.2 8B, costs $0.06 per million input tokens and $0.15 per million output (OpenRouter, cheapest active endpoint, checked 2026-11-01). 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 Spark-X2.6 1.7B

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

All 56 machines on this site run it at 32k, not just the eight in the table. 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 1M 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. 5 of the 8 above reach it, and the slowest is 73 tok/s.

The cheapest machine that runs it is sold with 16 GB. There is a page on what 16 GB runs, machine by machine: it names the 6 machines here sold at that size, and the 16 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 12 GB, on the GeForce RTX 3060, 12GB at $329, card only, which hands a model 11 GB and is no longer sold.

Run Spark-X2.6 1.7B at 256k on the Mac mini M6, 16GB

How much memory does Spark-X2.6 1.7B need at 256k?

Every figure above is priced at 32k of context. At 256k, the longest the calculator offers, Spark-X2.6 1.7B needs 4.9 GB rather than 1.6 GB. The weights are the same either way; the key-value cache goes from 0.5 GB to 3.8 GB.

The window costs nothing in hardware: all 37 machines here still sold at a published price hold Spark-X2.6 1.7B at both lengths, and the cheapest of them is the Mac mini M6, 16GB at $899.

On the Mac mini M6, 16GB it runs 73 tok/s estimated at 32k and 24 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

1.7B

Quantisation

Q4_K_M

Weights on disk

1.1 GB

KV cache

0.5 GB at 32k context — Spark-X2.6 4B's pattern over fewer layers: 3 sliding-window layers (512) per full-attention layer, 28 in place of 36, at two KV heads rather than four, so a cached token costs half as much in each layer that grows. The whole 1M window is 15.1 GB of cache against 1.09 GB of weights. How weights and cache add up.

Maximum context

1M tokens

Licence

Apache 2.0

Sources

XHToken/Spark-X2.6-1.7B, bartowski/Spark-X2.6-1.7B-GGUF, XHToken/Spark-X2.6-1.7B-GGUF