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

Can Llama 4 Maverick 17B 128E Instruct run on the H100 SXM?

Not fully in VRAM. Even at 2-bit with 8K context, Llama 4 Maverick 17B 128E Instruct needs about 138 GB, more than the 76.0 GB usable on the H100 SXM. It can still run with offload (slower): Q3_K_M with part of the model in system RAM, about 24–45 tokens/sec (estimate). Details and command.

Runs with offload (slower)

Runs with offload 3-bit (Q3_K_M) at 8K context: all attention layers plus the experts of 9 of 24 MoE layers on the H100 SXM (about 72.4 GB), and the experts of the other 15 layers in system RAM (about 107 GB). Needs a PC with at least 128 GB of system RAM. Estimated speed: 24–45 tokens/sec (usable for chat), versus a bandwidth ceiling of ~390 tok/s if it fit fully in VRAM.

llama-server -hf unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF:Q3_K_M -c 8192 -ngl 999 --n-cpu-moe 39 --no-mmproj

Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, raise --n-cpu-moe by 1-2; if VRAM is left over, lower it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.

+ 1.6 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model. llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •137 GB No138 GB No142 GB No160 GB No—
3-bit (Q3_K_M) •179 GB No180 GB No185 GB No203 GB No—
4-bit (Q4_K_M) •228 GB No228 GB No233 GB No251 GB No—
5-bit (Q5_K_M) •266 GB No267 GB No272 GB No290 GB No—
6-bit (Q6_K) •308 GB No308 GB No313 GB No331 GB No—
8-bit (Q8_0) •398 GB No399 GB No403 GB No421 GB No—
16-bit (F16/BF16) •748 GB No749 GB No753 GB No771 GB No—

• real GGUF file size from unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF. Speed is a bandwidth ceiling (3350 GB/s), not a benchmark. Methodology.

Hardware that does fit it

Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB

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

Llama 4 Maverick 17B 128E Instruct on every GPU and Mac · Every model that runs on the H100 SXM · Other models that fit 64 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 (meta-llama/Llama-4-Maverick-17B-128E-Instruct), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.