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
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. Sending images also loads the vision projector (mmproj) file. Calculator with image input on.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 137 GB No | 138 GB No | 142 GB No | 160 GB No | — |
| 3-bit (Q3_K_M) • | 179 GB No | 180 GB No | 185 GB No | 203 GB No | — |
| 4-bit (Q4_K_M) • | 228 GB No | 228 GB No | 233 GB No | 251 GB No | — |
| 5-bit (Q5_K_M) • | 266 GB No | 267 GB No | 272 GB No | 290 GB No | — |
| 6-bit (Q6_K) • | 308 GB No | 308 GB No | 313 GB No | 331 GB No | — |
| 8-bit (Q8_0) • | 398 GB No | 399 GB No | 403 GB No | 421 GB No | — |
| 16-bit (F16/BF16) • | 748 GB No | 749 GB No | 753 GB No | 771 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
- No listed GPU with a list price runs Llama 4 Maverick 17B 128E Instruct fully in memory. The smallest listed hardware that does is the Mac M2 Ultra 192GB (192 GB).
- Largest popular model that fits the H100 SXM: gpt-oss 120B (117B, MoE) at F16, about 61.9 GB at 8K context.
"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 2026-11-17; refreshed hourly.