RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?API pricesVRAM calculatorNew

Can MiniMax H3 Image PE run on the L40S?

Yes. At 8K context the best fit is Q8_0, using about 28.0 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~30 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •11.1 GB Fits11.3 GB Fits12.8 GB Fits18.8 GB Fits81
3-bit (Q3_K_M) •13.5 GB Fits13.8 GB Fits15.3 GB Fits21.3 GB Fits65
4-bit (Q4_K_M) •16.5 GB Fits16.8 GB Fits18.3 GB Fits24.3 GB Fits52
5-bit (Q5_K_M) •19.0 GB Fits19.3 GB Fits20.8 GB Fits26.8 GB Fits45
6-bit (Q6_K) •21.7 GB Fits21.9 GB Fits23.4 GB Fits29.4 GB Fits39
8-bit (Q8_0) •27.8 GB Fits28.0 GB Fits29.5 GB Fits35.5 GB Fits30
16-bit (F16/BF16)52.1 GB No52.3 GB No53.8 GB No59.8 GB No—

• real GGUF file size from mradermacher/MiniMax-H3-Image-PE-GGUF. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

MiniMax H3 Image PE on every GPU and Mac · Every model that runs on the L40S · Other models that fit 48 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (MiniMaxAI/MiniMax-H3-Image-PE), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.