Check my GPU →

Can the Mac 64 GB run MiniMax H3 Pruned?

Yes. 16-bit fits on the Mac 64 GB with 9.7 GB to spare.

Video model · pruned 33B64 GB unified · ~55.7 GB for the GPU · 273–800 GB/s · Apple SiliconData 2026-10-01
Runs well
Yes, with room to spare.

16-bit (40.2 GB) needs about 46.0 GB in use, so 9.7 GB of the 55.7 GB stays free: room for a larger image, a LoRA or a ControlNet.

Best file16-bit
File size40.2 GB
GPU memory needed~46.0 GB
Shared memory104 / 64 GB
Memory map · Mac 64 GB46.0 GB / 55.7 GB
028 GB56 GB
Weights 16-bit · 40.2 GBWorking memory · 5.0 GBReserve · 0.8 GBFree · 9.7 GB

01What to download

PartFileFolderSize
Modelminimax_h3_fl2va_pruned_bf16.safetensors
16-bit · Comfy-Org/MiniMax-H3
models/diffusion_models40.2 GBDownload →
Text encoderqwen3vl_32b_minimax_h3_bf16.safetensors
Qwen3-VL 32B BF16 · Comfy-Org/MiniMax-H3
models/text_encoders51.5 GBDownload →
VAEminimax_h3_video_vae_fp16.safetensors
MiniMax H3 video VAE FP16 · Comfy-Org/MiniMax-H3
models/vae5.2 GBDownload →
Also neededminimax_h3_audio_vae_fp32.safetensors
MiniMax H3 audio VAE FP32 · Comfy-Org/MiniMax-H3
models/vae0.6 GBDownload →
Total download · keep about the same free on disk97.5 GB

On a Mac, FP8 text encoders do not load, so a 16-bit one is listed. Sizes from Hugging Face, 2026-10-01.

Shared memory: about 103.5 GB of your 64 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That is about 39.5 GB more than there is. It still runs: while the model works, the system compresses or swaps the idle text encoder, so loading and changing the prompt get slower. A smaller file or text encoder avoids that. calculated

02Every MiniMax H3 Pruned file on 55.7 GB

FileSizeNeededOn this cardQualityDownload
16-bit ←
SAFETENSORS · Comfy-Org
40.2 GB46.0 GBfits · 9.7 GB sparethe original weightsHugging Face →
Q8_0
GGUF · Abiray
21.6 GB27.4 GBfits · 28.3 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · Abiray
16.7 GB22.5 GBfits · 33.2 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · Abiray
14.1 GB19.9 GBfits · 35.8 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · Abiray
11.6 GB17.4 GBfits · 38.3 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · Abiray
8.9 GB14.7 GBfits · 41.0 GB sparenoticeable loss of detailHugging Face →

“Needed” adds 5 GB of working memory for MiniMax H3 Pruned and a 0.8 GB reserve. Sizes 2026-10-01. 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.

03Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run MiniMax H3 Pruned on a Mac 64 GB, send your time per image and peak VRAM and it will appear here, credited.

04About the Mac 64 GB

A Mac with 64 GB shares that memory between the CPU and the GPU. On current macOS the GPU may use about 55.7 GB of it by default (older macOS versions: about 51.5 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 64 GB: M1 Max, M1 Ultra, M2 Max, M2 Ultra, M3 Max, M4 Pro, M4 Max, M5 Pro, M5 Max (memory bandwidth 273–800 GB/s - the higher, the faster). Everything about Macs and local AI →

64 GB unified · ~55.7 GB for the GPU · 273–800 GB/s · Apple Silicon. Everything that runs on it →

05Questions

How much VRAM does MiniMax H3 Pruned need?

Around 14.7 GB with the smallest file (Q3_K_M) and 26.8 GB with an 8-bit file (FP8). The full 16-bit file needs about 46.0 GB.

Which MiniMax H3 Pruned file should I download for the Mac 64 GB?

16-bit (40.2 GB) from Comfy-Org/MiniMax-H3.

FP8 or Q8_0 for MiniMax H3 Pruned on the Mac 64 GB?

Q8_0 (21.6 GB). The Mac 64 GB has no FP8 maths, so FP8 (21.0 GB) only saves memory and is a step further from the original.

How much do I need to download for MiniMax H3 Pruned on the Mac 64 GB?

97.5 GB: minimax_h3_fl2va_pruned_bf16.safetensors, qwen3vl_32b_minimax_h3_bf16.safetensors, minimax_h3_video_vae_fp16.safetensors, minimax_h3_audio_vae_fp32.safetensors.