GLM 5.3 Flash VRAM: 320B With a 1M Window, on Two Sparks

GLM 5.3 Flash VRAM Requirements: The Short Answer

Running Z.ai’s newest frontier MoE takes 186 GiB at Q4_K_M, 129 GiB at Q3_K_M, and still 101 GiB at the bottom of the quant ladder. No gaming card on the market holds any of those numbers. The only measured runs published so far are on DGX Sparks, two of them, and both are in our tokens per second tool. The surprise sits in the second column: taking context from 8K tokens to the full 1,048,576 costs 14 GiB, total, on a 320 billion parameter model.

Here is the whole table, from our calculator, llama.cpp backend, weights plus cache plus overhead. These are capacity figures, not speed promises.

Read the columns, not the rows. A normal model’s memory fan-outs as context grows; this one barely breathes. From 8K to a million tokens, every tier moves by roughly 14 GiB, less than many 24 GB models move crossing 128K. The rest of this piece explains where that 14 comes from, what hardware clears the bar, and why a same-day Qwen release gives the same 128 GB machine a completely different answer.

The Stealth Week, and Our Receipt

For seven days before the announcement, a model called Ox Alpha served on OpenCode under no name and no lab. Mid-session on 21 August, its thinking and output flipped to Chinese characters for a few seconds, then back. The next day we posted the screenshot with the conclusion the behaviour pointed to:

Many are speculating about the origin of Ox Alpha. Mid-session yesterday, the thinking and the output automatically switched to Chinese characters for a few seconds before returning to English. The thinking process and the work are very similar to GLM’s. x.com/VRAMCalculator

Four days later Z.ai confirmed it from the other side, pinning that GLM 5.3 Flash was “previously previewed as Ox Alpha, running entirely on Chinese AI chips“. OpenCode followed, moving the renamed model onto OpenCode Go. Behaviour gave the lab away before anyone official did. We mention it once, because it is ours, and get back to the hardware.

Why a Million Tokens Only Costs 14 GiB

The spec sheet explains the curve. Every figure below is from zai-org/GLM-5.3-Flash and its config.json, read the day the weights landed.

Thirty four of the forty five layers hold a fixed size state, like shelving rented by the unit rather than by the box stacked on it. Rent the shelf once and the bill never changes, however full your warehouse gets. Only the 11 sparse MLA layers keep a cache that grows with tokens, and theirs is compressed to a 512 wide latent per position instead of a full key and value copy. Multiply that compression across eleven layers and a million positions and you get the 14 GiB.

The pattern holds in the table. Q4_K_M goes 185.9, 186.2, 189.3, 199.9 across the context ladder. The jump from 8K to 1M is 14.0 GiB. At Q8_0 it is also 14.0. Q3_K_M spreads 128.7 to 142.7, again 14.0. The context surcharge does not care which quant you pick, because at these settings the cache is not what gets quantized.

Z.ai frames the design the same way in its own card: “for the first time in the GLM series, we introduce a hybrid architecture combining sparse and linear attention, sharply reducing long-context serving costs while preserving precise long-context capabilities.”

What Hardware Actually Clears the Floor

Start at the top of the consumer market. An RTX 5090 carries 32 GB. The cheapest entry in the table needs three times that at minimum context, so the entire gaming stack, 8 GB through 32 GB, is out before the discussion starts.

Unified memory changes the conversation, which is why the next section matters. Between a Spark and a rack sit the large-memory workstations and Mac Studios, and the honest read of the table is:

• Under 120 GiB usable: Q2_K fits on paper at short context and climbs to 115.0 at the full million. Whether 2-bit quality on an MoE this sparse holds up is an open question nobody has answered publicly yet.
• Around 190 to 200 GiB usable: Q4_K_M through the full 1M window, with margin at everyday contexts.
• 340 GiB or more: Q8_0 anywhere on the ladder.

Day-one runtime support is real rather than aspirational: the card lists SGLang, vLLM, TokenSpeed and KTransformers.

Same-Day Releases, Opposite Answers on the Same Box

The most useful comparison landed the same day the weights did. Alibaba opened Qwen3.8-Flash-Next, 180B at 3.3% active, and our requirements page for it records Q4 at 256K context at 110 GB, sized for one DGX Spark.

GLM 5.3 Flash does not fit it, and the table says so precisely: Q4_K_M starts at 185.9 GiB against 128 GB of unified memory, and even Q3_K_M at 128.7 GiB is over the line before overhead. Two frontier-class MoEs, launched the same day, straddling the exact machine enthusiasts actually bought this year. Capacity math is the only fair referee here, because the same five GPUs face both models and give opposite verdicts. If you sized a purchase around Flash-Next, GLM 5.3 Flash resets that arithmetic.

The Benchmarks, Priced in Hardware

Z.ai published its launch numbers itself, as evaluation results on the model repo: Terminal-Bench 2.1 at 84.3, DeepSWE at 63.4, HLE at 55.3. Around them the card supplies the headline in Z.ai’s own words: “approaching Claude Opus 4.8 on coding and agentic benchmarks”. Vendor figures, all of them, and no independent evaluation has landed yet.

Follow those numbers to the desk and they stop being abstract. A benchmark tier like that only becomes real if you can host the model at a quant worth running and a context worth filling, and our table prices that hosting at 185.9 GiB for Q4_K_M, rising to 199.9 GiB across the full million-token window. One Spark holds neither figure. A second Spark gets the pool past the number, at doubled complexity, and a large workstation does it in one unit. On paper the model plays in frontier company; on our table, so does the hardware bill.

The same week supplies its own counterweight. Qwen3.8-Flash-Next ranked ahead of Claude Opus 4.6 in Alibaba’s launch material and still hosts Q4 at 256K on one box, 110 GB per our requirements page. So the reader’s decision this week is not which scorecard wins. It is which set of trade-offs fits the memory already on the desk, and owning the weights keeps the usual levers open either way: a lower rung on the ladder, a trimmed cache, tuned flags. The table at the top prices every one of those steps.

Total Parameters Buy the Card. Active Parameters Buy the Speed

Three releases inside one week make the point better than any explainer we could write, and our MoE conversion piece made it first: Qwen3.8-27B Whittle runs 66% of parameters per token, GLM 5.3 Flash runs 5.6%, Flash-Next runs 3.3%. Total size determines whether the model fits your memory at all. Active size drives how fast it generates once resident.

So a reader who hears “320B impossible at home” and “only 18B, trivially light” is being sold two halves of one wrong picture. The card wants the whole file. Your tok/s cares about the slice. Speed on specific home hardware will be somebody else’s measurement before it is ours, and when those numbers surface they land on this page the way every other launch page here handled it.

Checking Your Own Machine

Select glm53-flash in the calculator to reproduce every figure in the table at your own context length and see the component split: weights, cache, runtime allowance. Working backwards from a card you own, the GPU-first tool lists everything in the catalogue your hardware holds today, including the two Flash siblings on either side of this one. The gap between them, 110 GB versus 186 GiB at Q4, is currently the widest spread between two same-week releases we have measured.

FAQ

How much VRAM does GLM 5.3 Flash need?

At least 101.1 GiB at Q2_K with 8K context, 185.9 GiB at the more practical Q4_K_M, and 325.0 GiB if you want near-lossless Q8_0. Those totals include weights, KV cache and a runtime allowance, computed with the llama.cpp profile in our calculator.

Can a DGX Spark run GLM 5.3 Flash?

No, not at 3-bit precision or better. The Spark offers 128 GB of unified memory, about 119 GiB usable, while Q3_K_M alone needs 128.7 GiB. Qwen3.8-Flash-Next, launched the same day, does fit that same box at Q4.

Why does the 1M context only add 14 GiB?

Because 34 of the model’s 45 layers hold a fixed size state that never grows, and only the 11 sparse MLA layers store a per-token cache, compressed to a 512 wide latent. Eleven cheap caches times a million tokens equals roughly 14 GiB.

Is the context cost the same at every quant level?

In this table, effectively yes: 14.0 GiB at Q8_0 and Q4_K_M, 14.0 at Q3_K_M and 13.9 at Q2_K. The cache is kept at full width while the weights carry the quantization.

What was Ox Alpha?

The working name under which GLM 5.3 Flash ran anonymously on OpenCode for about a week. Z.ai’s launch post confirms the lineage, adding that the preview ran entirely on Chinese AI chips.

Which runtimes support GLM 5.3 Flash on day one?

SGLang, vLLM, TokenSpeed and KTransformers, per the official model card, each with published recipes or cookbooks.