What hardware do you need to run Spark-X2.6 4B?

Spark-X2.6 4B at Q4_K_M is 3.5 GB of weights, with a context ceiling of 1M tokens. Dense 4B built for on-device agents, with a native million-token context and three thinking levels. XHToken says it keeps Spark-X2.5 4B's architecture exactly and gains from post-training alone. On the cheapest machine that runs it, a Mac mini M6, 16GB, it generates 24 tok/s at 32k of context, worked out from memory bandwidth.

How good is Spark-X2.6 4B, really?

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

What Spark-X2.6 4B costs either way

Nobody rents Spark-X2.6 4B by the token. The closest hosted match, Granite 4.2 8B, costs $0.06 per million input tokens and $0.25 per million output (OpenRouter, cheapest active endpoint, checked 2026-10-24). 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 4B

Every machine here runs it, but not to the same length. The Mac mini M6, 16GB stops at 128k; the Strix Halo Framework Desktop, 32GB takes it to 256k, the longest the calculator offers. The weights are the same size on every machine; what differs is the memory left for the key-value cache, which grows with every token you keep.

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. 2 of the 8 above reach it, and the slowest is 24 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 14 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 4B at 256k on the Strix Halo Framework Desktop, 32GB

How much memory does Spark-X2.6 4B need at 256k?

Every figure above is priced at 32k of context. At 256k, the longest the calculator offers, Spark-X2.6 4B needs 13.3 GB rather than 4.8 GB. The weights are the same either way; the key-value cache goes from 1.3 GB to 9.7 GB.

All 37 machines here still sold at a published price hold Spark-X2.6 4B at 32k and 33 hold it at 256k. The cheapest still sold goes from the Mac mini M6, 16GB at $899 to the Mac mini M6, 24GB at $1,099.

On the Mac mini M6, 24GB it runs 27 tok/s estimated at 32k and 9.6 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

4.1B

Quantisation

Q4_K_M

Weights on disk

3.5 GB

KV cache

1.3 GB at 32k context — 3 sliding-window layers (512) per full-attention layer, which is what makes a million-token context tractable at this size. The shape is Spark-X2.5 4B's exactly, down to the parameter count, so the cache costs the same; the four-bit download does not, at 3.54 GB against 2.60 GB. How weights and cache add up.

Maximum context

1M tokens

Licence

Apache 2.0

Sources

XHToken/Spark-X2.6-4B, XHToken/Spark-X2.6-4B-GGUF