Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

Can the Mac 128 GB run HunyuanVideo 1.5?

Video model · 8.3B128 GB unified · ~115.4 GB for the GPU · 300–800 GB/s · Apple SiliconData 2026-09-25
Runs well
Yes — and comfortably.

Download 16-bit (16.7 GB). With the model's working memory it needs about 21.0 GB, leaving 94.4 GB spare on 115.4 GB. Quality: the original weights.

Best file16-bit
File size16.7 GB
GPU memory needed~21.0 GB
Shared memory42 / 128 GB
Memory map · Mac 128 GB21.0 GB / 115.4 GB
058 GB115 GB
Weights 16-bit · 16.7 GBWorking memory · 3.5 GBReserve · 0.8 GBFree · 94.4 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

01What to download

PartFileFolderSize
Modelhunyuanvideo1.5_720p_t2v_fp16.safetensors
16-bit · Comfy-Org/HunyuanVideo_1.5_repackaged
models/diffusion_models16.7 GBDownload →
Text encoderqwen_2.5_vl_7b.safetensors
Qwen2.5-VL 7B BF16 · Comfy-Org/HunyuanVideo_1.5_repackaged
models/text_encoders16.6 GBDownload →
Text encoderbyt5_small_glyphxl_fp16.safetensors
ByT5 small GlyphXL FP16 · Comfy-Org/HunyuanVideo_1.5_repackaged
models/text_encoders0.4 GBDownload →
VAEhunyuanvideo15_vae_fp16.safetensors
HunyuanVideo 1.5 VAE FP16 · Comfy-Org/HunyuanVideo_1.5_repackaged
models/vae2.5 GBDownload →
Total download · keep about the same free on disk36.2 GB

Only for some workflows: SigCLIP vision patch14 384 (0.9 GB, I2V only). On a Mac, FP8 text encoders do not load, so a 16-bit one is listed. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.

Shared memory: about 42.2 GB of your 128 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That leaves room, so nothing has to be swapped to disk. calculated

02Every HunyuanVideo 1.5 file on 115.4 GB

FileSizeNeededOn this cardQualityDownload
16-bit ←
SAFETENSORS · Comfy-Org
16.7 GB21.0 GBfits · 94.4 GB sparethe original weightsHugging Face →
Q8_0
GGUF · jayn7
9.0 GB13.3 GBfits · 102.1 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · jayn7
7.0 GB11.3 GBfits · 104.1 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · jayn7
6.1 GB10.4 GBfits · 105.0 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · jayn7
5.1 GB9.4 GBfits · 106.0 GB sparegood; some loss in fine detail and textHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 3.5 GB working memory for this model + 0.8 GB kept free for the system. FP8 and INT8 files are left out on a Mac: Apple GPUs cannot compute FP8, so ComfyUI either fails to load them or converts them back to 16-bit, which saves no memory. Use a 16-bit or GGUF file.

03The text encoder

Qwen2.5-VL 7B + glyph encoder: 16.6 GB as 16-bit, 9.4 GB as FP8. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 115.4 GB the FP8 encoder fits on its own, so prompt encoding stays fast.

04About this GPU

A Mac with 128 GB shares that memory between the CPU and the GPU. On current macOS the GPU may use about 115.4 GB of it by default (older macOS versions: about 103.1 GB); that is the figure used here. ComfyUI can go past it, but macOS then starts compressing and swapping memory and everything slows down. ComfyUI runs on Apple GPUs through PyTorch's MPS backend. 16-bit and GGUF files work; FP8 and INT8 files do not save memory on a Mac, so they are skipped. Speed is the catch: even the fastest Macs are several times slower per image than a desktop RTX card. Chips sold with 128 GB: M1 Ultra, M2 Ultra, M3 Max, M4 Max, M5 Max (memory bandwidth 300–800 GB/s — the higher, the faster). Everything about Macs and local AI →

Mac 128 GB: 128 GB unified · ~115.4 GB for the GPU · 300–800 GB/s · Apple Silicon. Everything that runs on the Mac 128 GB →

05What more VRAM would change

Nothing to gain for this model: the Mac 128 GB already runs a top-quality file entirely in VRAM. More memory would only help with bigger images, longer clips or several models at once.

06Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run HunyuanVideo 1.5 on a Mac 128 GB, send your time per image and peak VRAM and it will appear here, credited.

07Questions

How much VRAM does HunyuanVideo 1.5 need?

Around 9.4 GB with the smallest file (Q4_K_M) and 12.6 GB with an 8-bit file (FP8), counting working memory and a small system reserve. The full 16-bit file needs about 21.0 GB.

Which HunyuanVideo 1.5 file should I download for the Mac 128 GB?

16-bit (16.7 GB) from Comfy-Org/HunyuanVideo_1.5_repackaged.

Is FP8 faster than GGUF on the Mac 128 GB?

No. This GPU has no FP8 compute, so ComfyUI converts FP8 weights back before the maths. FP8 only saves memory here; Q8_0 GGUF is the closer-to-original 8-bit pick.

How much do I need to download for HunyuanVideo 1.5 on the Mac 128 GB?

About 36.2 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 115.4 GB card, 48 GB of system RAM or more is recommended.