Can I run Hy4 preview on a Mac?

On memory, yes: Hy4 preview fits 2 of 54 Macs in the LLMCheck index (runtime caveat below). It needs about 292 GB of unified memory at a 4K context and about 298 GB at 64K. Smallest and fastest current Mac: the Mac Studio M5 Ultra 512 GB (~14 tok/s est.); none reaches 15 tok/s. No measured run yet.

Mac runtime caveat

llama.cpp has its hy_v4 architecture from b10813, but it was validated only on CUDA and no Mac run has been published; MLX needs an unmerged mlx-lm branch.

RAM at 4K
292
GB
RAM at 64K
298
GB, 16-bit KV
Macs that run it
2
of 54 configs
Best measured
—
no measured run

Hy4 preview on every Mac

One row per Mac configuration, grouped by product line. The build is the one each speed is for; the context column is the longest prompt that fits inside macOS’s default GPU memory limit with a 16-bit KV cache (“raised” where the limit has to be raised first; “full” when the whole window fits). Speeds are decode tok/s from the LLMCheck index, each with its provenance mark. For large mixture-of-experts models (over 40B total), the formula’s typical error is about 34% (the median gap to 70 measured plain-decode runs; it tends to undershoot (median −33%), and an estimate scaled from the model’s own measured run is usually closer; method).

Runs fits macOS’s default GPU limit, 15+ tok/sRuns, slowly fits, under 15 tok/sRaise GPU limit fits once the limit is raised (command below)Doesn't fit needs more memory than the Mac has
MacVerdictBuildSpeedMax contextModel page
MacBook Air
MacBook Air M5 16 GBDoesn't fit————
MacBook Air M5 24 GBDoesn't fit————
MacBook Air M5 32 GBDoesn't fit————
MacBook Air M1 8 GB refurbDoesn't fit————
MacBook Air M4 16 GB usedDoesn't fit————
MacBook Air M2 16 GB refurbDoesn't fit————
MacBook Air M3 16 GB refurbDoesn't fit————
MacBook Air M1 16 GB refurbDoesn't fit————
MacBook Air M4 24 GB usedDoesn't fit————
MacBook Air M2 24 GB refurbDoesn't fit————
MacBook Air M3 24 GB refurbDoesn't fit————
MacBook Pro
MacBook Pro M6 16 GBDoesn't fit————
MacBook Pro M5 Pro 24 GBDoesn't fit————
MacBook Pro M6 24 GBDoesn't fit————
MacBook Pro M6 32 GBDoesn't fit————
MacBook Pro M5 Pro 48 GBDoesn't fit————
MacBook Pro M5 Max 64 GBDoesn't fit————
MacBook Pro M5 Pro 64 GBDoesn't fit————
MacBook Pro M5 Max 128 GBDoesn't fit————
MacBook Pro M3 Max 64 GB refurbDoesn't fit————
MacBook Pro M3 Max 128 GB refurbDoesn't fit————
Mac mini
Mac mini M6 16 GBDoesn't fit————
Mac mini M5 Pro 24 GBDoesn't fit————
Mac mini M6 24 GBDoesn't fit————
Mac mini M6 32 GBDoesn't fit————
Mac mini M5 Pro 48 GBDoesn't fit————
Mac mini M5 Pro 64 GBDoesn't fit————
Mac mini M2 Pro 16 GB refurbDoesn't fit————
Mac mini M4 16 GB usedDoesn't fit————
Mac mini M4 Pro 24 GB usedDoesn't fit————
Mac mini M4 24 GB usedDoesn't fit————
Mac mini M2 Pro 32 GB refurbDoesn't fit————
Mac mini M4 Pro 48 GB usedDoesn't fit————
Mac mini M4 Pro 64 GB usedDoesn't fit————
iMac
iMac M6 16 GBDoesn't fit————
iMac M6 24 GBDoesn't fit————
iMac M6 32 GBDoesn't fit————
Mac Studio
Mac Studio M5 Max 36 GBDoesn't fit————
Mac Studio M5 Max 48 GBDoesn't fit————
Mac Studio M5 Max 64 GBDoesn't fit————
Mac Studio M5 Ultra 96 GBDoesn't fit————
Mac Studio M5 Max 128 GBDoesn't fit————
Mac Studio M5 Ultra 256 GBDoesn't fit————
Mac Studio M5 Ultra 512 GBRuns, slowlyQ4_K_Mestimated14 tok/s1M (full)M5 Ultra page
Mac Studio M2 Max 32 GB refurbDoesn't fit————
Mac Studio M1 Ultra 64 GB refurbDoesn't fit————
Mac Studio M4 Max 64 GB usedDoesn't fit————
Mac Studio M2 Max 64 GB refurbDoesn't fit————
Mac Studio M1 Ultra 128 GB refurbDoesn't fit————
Mac Studio M2 Ultra 128 GB refurbDoesn't fit————
Mac Studio M4 Max 128 GB usedDoesn't fit————
Mac Studio M2 Ultra 192 GB refurbDoesn't fit————
Mac Studio M3 Ultra 256 GB usedDoesn't fit————
Mac Studio M3 Ultra 512 GB refurbRuns, slowlyQ4_K_Mestimated9 tok/s1003K—
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Context memory is computed from its config.json (MLA on all 78 layers (kv_lora_rank 512 + rope 64); DSA lightning-indexer keys (index_head_dim per layer) not counted; runtimes that expand MLA to per-head K/V use far more): about 5.9 GB of 16-bit KV cache at 64K tokens. A q8 cache (llama.cpp -ctk q8_0 -ctv q8_0, Ollama OLLAMA_KV_CACHE_TYPE=q8_0) halves that part. Runtimes also grow a compute buffer with context, so a fit within about 1 GB of the limit is optimistic.

macOS’s GPU memory limit

macOS lets the GPU use only part of unified memory by default. Hy4 preview fits inside that default limit on every Mac it fits at all, so no Mac in the table needs it raised at a short context. Long contexts may still need it: the context column already uses each Mac’s default limit.

Hy4 preview: memory by quantization

Weights are 770B parameters at each format’s effective size (the index’s GB-per-billion table), plus about 2 GB for the runtime and a short context; longer contexts add the KV cache computed from the model’s config.json at 16 bits. It is a mixture-of-experts model: all 770B parameters sit in memory although only 49B are read per token. The first row is the catalog’s own figure (about 292 GB at a 4K context), the one every verdict on this page uses. “Smallest Mac” is the smallest memory size among the Macs Apple sells new that holds it at a 4K context inside that Mac’s default GPU limit. Estimates, not measurements.

BuildWeightsRAM at 4Kat 32Kat 64KSmallest Mac
As catalogued—292 GB295 GB298 GB512 GB
Q2_K261.8 GB264 GB266 GB269 GB512 GB
Q3_K_M377.3 GB379 GB382 GB385 GB512 GB
Q4_K_M438.9 GB441 GB443 GB446 GB512 GB
Q5_K_M546.7 GB549 GB551 GB554 GBnone (over 512 GB)
Q6_K631.4 GB633 GB636 GB639 GBnone (over 512 GB)
Q8_0816.2 GB818 GB821 GB824 GBnone (over 512 GB)
F161540.0 GB1542 GB1545 GB1548 GBnone (over 512 GB)

Measured runs

The index holds no published or community run of Hy4 preview yet, so every speed on this page is an estimate from the memory-bandwidth model. LLMCheck runs no tests of its own: if you have run it on a Mac, submit the figure with its setup →

Recommended setup

Before you start: llama.cpp has its hy_v4 architecture from b10813, but it was validated only on CUDA and no Mac run has been published; MLX needs an unmerged mlx-lm branch.

The index has no verified Ollama tag for Hy4 preview. Start from its listing and copy the exact name of a build that fits: Hugging Face repo → · model card →

GGUF builds run in LM Studio or llama.cpp; MLX builds run in LM Studio or mlx-lm.

On the Mac Studio M5 Ultra (512 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~14 tok/s (estimated) at Q4_K_M; keep the context at or under 1M there, or use a q8 KV cache.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Hy4 preview

Mac Studio M5 Ultra (512 GB) — smallest current Mac that runs it, $22,299 new (Apple list price, checked 2026-11-14), ~14 tok/s (estimated). Amazon does not stock the Mac Studio M5 Ultra (512 GB): Apple builds it to order.

FAQ: Hy4 preview on a Mac

Can I run Hy4 preview on a Mac?

On memory, yes (its Mac runtime carries a caveat: llama.cpp has its hy_v4 architecture from b10813, but it was validated only on CUDA and no Mac run has been published; MLX needs an unmerged mlx-lm branch). Hy4 preview needs about 292 GB of unified memory at a short (4K-token) context, so it runs on 2 of the 54 Mac configurations in the LLMCheck index. The smallest Mac Apple sells new that runs it is the Mac Studio M5 Ultra (512 GB).

How much RAM does Hy4 preview need?

About 292 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 295 GB in total at 32K and 298 GB at 64K with the default 16-bit cache (about 295 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Hy4 preview run on a Mac?

On an M5 Ultra, the chip the leaderboard quotes it on, the index figure is ~14 tok/s (estimated) at Q4_K_M. No published or community run is in the index yet; every speed is an estimate from the memory-bandwidth model. Every Mac’s figure is in the table on this page with its provenance: published, community run or estimated.

What is the cheapest Mac that runs Hy4 preview well?

No Mac Apple sells new reaches 15 tok/s with Hy4 preview. The fastest is the Mac Studio M5 Ultra (512 GB) at ~14 tok/s (estimated): fine for batch work, slow for chat.

Do I need to raise the GPU memory limit to run Hy4 preview?

No. On all 2 Mac configurations where Hy4 preview fits, it fits inside that Mac’s default GPU memory limit at a short context; only a long context on the smallest of them can push it over.

Which quantization of Hy4 preview should I use?

Q4_K_M (about 439 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 816 GB) is closer to full quality and needs more memory than any Mac has. Q3_K_M and Q2_K shrink it to about 377 and 262 GB at a quality cost. The index’s reference figure (14 tok/s on an M5 Ultra) is for its Q4_K_M build.

How much context can Hy4 preview use on a Mac?

Its own window is 1M tokens. At macOS’s default GPU limit, the Mac Studio M5 Ultra (512 GB) holds about 1M (the full window).

Cite this page

LLMCheck. (2026). Can I run Hy4 preview on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/hy4-preview/ (updated ). CC BY 4.0.

How to cite LLMCheck →Data: CC BY 4.0Markdown version

Related

Figures from the LLMCheck index, data version 2026-11-18. Verdicts and context limits are estimates from each model’s catalog memory figure and config.json.