Check my GPU →

Can the Radeon 8060S (Strix Halo) 96 GB run MiniMax H3 (33B)?

Yes. 16-bit fits on the Radeon 8060S (Strix Halo) 96 GB with 23.9 GB to spare.

Video model · 33.1B96 GB LPDDR5X (shared system memory) · 256-bit · 256 GB/s · RDNA 3.5Data 2026-10-01
Runs well
Yes, with room to spare.

16-bit (66.3 GB) needs about 72.1 GB in use, so 23.9 GB of the 96 GB stays free: room for a larger image, a LoRA or a ControlNet.

Best file16-bit
File size66.3 GB
GPU memory needed~72.1 GB
Shared memory105 / 128 GB
Memory map · Radeon 8060S (Strix Halo) 96 GB72.1 GB / 96 GB
048 GB96 GB
Weights 16-bit · 66.3 GBWorking memory · 5.0 GBReserve · 0.8 GBFree · 23.9 GB

01What to download

PartFileFolderSize
Modelminimax_h3_fl2va_bf16.safetensors
16-bit · Comfy-Org/MiniMax-H3
models/diffusion_models66.3 GBDownload →
Text encoderqwen3vl_32b_minimax_h3_int8_convrot.safetensors
Qwen3-VL 32B INT8 (convrot) · Comfy-Org/MiniMax-H3
models/text_encoders27.1 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 disk99.2 GB

Alternatives: Qwen3-VL 32B NVFP4 (AWQ) (15.7 GB); Qwen3-VL 32B BF16 (51.5 GB). FP4 files are listed only as alternatives unless the GPU is an RTX 50 (Blackwell). Sizes from Hugging Face, 2026-10-01.

Shared memory: about 105.2 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 MiniMax H3 file on 96 GB

FileSizeNeededOn this cardQualityDownload
16-bit ←
SAFETENSORS · Comfy-Org
66.3 GB72.1 GBfits · 23.9 GB sparethe original weightsHugging Face →
Q8_0
GGUF · Abiray
36.0 GB41.8 GBfits · 54.2 GB sparepractically identical to the originalHugging Face →
INT8
SAFETENSORS · Comfy-Org
34.0 GB39.8 GBfits · 56.2 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · Abiray
28.2 GB34.0 GBfits · 62.0 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · Abiray
23.9 GB29.7 GBfits · 66.3 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · Abiray
19.9 GB25.7 GBfits · 70.3 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · Abiray
15.6 GB21.4 GBfits · 74.6 GB sparenoticeable loss of detailHugging Face →

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

03Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run MiniMax H3 on a Radeon 8060S (Strix Halo) 96 GB, send your time per image and peak VRAM and it will appear here, credited.

04About the Radeon 8060S (Strix Halo) 96 GB

This is an integrated GPU that uses system memory. AMD states that up to 96 GB of the 128 GB can be set aside as graphics memory on Windows, which is why it can hold models no consumer graphics card can. The catch is speed: the GPU itself (40 compute units) is far smaller than a big desktop card, and its memory bandwidth is a fraction of one, so each step takes much longer. Treat the verdicts here as 'it fits', not 'it is fast'.

96 GB LPDDR5X (shared system memory) · 256-bit · 256 GB/s · RDNA 3.5. Everything that runs on it →

05Questions

How much VRAM does MiniMax H3 need?

Around 21.4 GB with the smallest file (Q3_K_M) and 39.8 GB with an 8-bit file (INT8). The full 16-bit file needs about 72.1 GB.

Which MiniMax H3 file should I download for the Radeon 8060S (Strix Halo) 96 GB?

16-bit (66.3 GB) from Comfy-Org/MiniMax-H3.

How much do I need to download for MiniMax H3 on the Radeon 8060S (Strix Halo) 96 GB?

99.2 GB: minimax_h3_fl2va_bf16.safetensors, qwen3vl_32b_minimax_h3_int8_convrot.safetensors, minimax_h3_video_vae_fp16.safetensors, minimax_h3_audio_vae_fp32.safetensors.