GuidesLocal video

LTX 2.5 now fits
a 16 GB Mac.

The 32 GB floor falls. Kynd's streamed engine renders a five-second LTX 2.5 Ingredients clip in a measured 13.3 GB peak — down from 28 — with checksum-identical output.

Four frames of a consistent character walking through a candlelit gothic church, rendered locally in a 13.3 GB peak Actual output of the 13.3 GB render
MLX video · Apple Silicon

Same pixels.
Half the
memory.

Three engine changes. One measured 13.3 GB peak.

Quick answer

From the next Kynd update, 16 GB Apple Silicon Macs run LTX 2.5's one-stage tiers locally — draft, balanced, and the experimental Ingredients route at its official 768×448 geometry — through a new streamed engine with a measured 13.3 GB peak for a five-second clip. The 32 GB resident route is unchanged, byte for byte.

Local video's hard wall has always been unified memory. Metal doesn't swap; it aborts. So when LTX 2.5's engine held its text encoder, connector and 22-billion-parameter transformer resident at once, the measured 28 GB peak made 32 GB an honest floor. The fix wasn't a smaller model. It was refusing to hold everything at once.

The memory ladder, measured.

EngineWhat changed5 s Ingredients peak
ResidentEverything loaded at once (the 32 GB-era engine)≈ 28 GB
StagedText encode and denoise phases never co-resident27.3 GB
+ StreamedTransformer weights stream per block; prompt embeds cached17.6 GB
Shorter clips go lower.A two-second Ingredients take peaks at a measured 9.4 GB. Plain text-to-video tiers sit below the Ingredients numbers because they carry no doubled reference token stream.

Three changes, in plain language.

1 · Staged phases

Never two giants at once

  • The 12 B text encoder runs while the transformer slot is empty.
  • Embeddings hand off; the encoder is freed.
  • Then the transformer loads for the denoise.
  • Repeat prompts skip the encoder entirely via a small on-disk embedding cache.
3 · Tiled decode

Half a frame at a time

  • Turning latents into pixels was the single largest spike.
  • The frame decodes as two overlapping halves.
  • A 128-px cross-fade joins them — measured 45.6 dB PSNR against untiled.
  • The seam runs through faces without a trace.

Proof, not promises.

Streaming changes when weights occupy memory, never what the model computes — so the streamed engine's raw output was checksummed against the resident engine's on identical seeds, at both two and five seconds. The checksums match exactly. Tiled decode blends a seam, so it is held to a different standard: 45.6 dB PSNR against the untiled frame, with the worst frame at 45.1 dB — comfortably beyond the threshold where differences stop being visible. It ships off by default; only low-memory tiers opt in.

Speed held too. Streaming costs between 1.5 and 11 percent per render, and repeated prompts come out faster than the old engine, because the embedding cache skips the multi-gigabyte text encoder pass entirely.

What a 16 GB Mac gets.

TierResolutionUnified memoryMeasured peak
2.5 draft512 × 32016 GB+≈ 13 GB
2.5 balanced704 × 44816 GB+≈ 13 GB
2.5 quality (two-stage)768 × 51248 GB+ · unchanged≈ 29 GB
Labelled honestly.The 16 GB tiers ship as experimental first: 13.3 GB is a tighter envelope than Kynd's usual gates, and real-world reports will decide when the label comes off. Macs with 24 GB or more get the same streamed engine with generous headroom, and the existing 32 GB resident route is untouched.

16 GB LTX 2.5 FAQ.

Can a 16 GB MacBook Air really run LTX 2.5?

Yes, from the next Kynd update, on the one-stage tiers through the streamed engine. Kynd unloads chat models before video renders, and the tier is labelled experimental while the 13.3 GB envelope gathers real-world mileage.

Is the quality reduced to make it fit?

No. Same model, same weights, same steps. The streamed denoise is checksum-identical to the resident engine; tiled decode measures 45.6 dB PSNR against the untiled path, which is visually indistinguishable.

What about the compact LTX 2.3 route?

It remains available and is still the lightest option. But 16 GB Macs no longer trade down to 2.3 for reference-conditioned work — the Ingredients route that produces consistent characters is a 2.5 capability, and it now fits.

Does this change 32 GB and larger Macs?

Their default route is byte-unchanged. They also gain the prompt-embedding cache, which makes repeat renders start faster.

The wall was residency, not the Mac.

Kynd measures the peak, gates the tier, and streams what never needed to sit in memory whole.

Next Mac guide

Run LTX 2.3 or 2.5 — the full tier guide.

Match the build to your Mac →