The LLMCheck index estimates Nemotron 3 Ultra 550B-A55B at ~12 tok/s on an M5 Ultra at Q4_K_M, a figure from its published bandwidth model, not a measured run. It needs about 226 GB of unified memory. It is NVIDIA's 550B mixture-of-experts model (55B active), released under the OpenMDW licence.
Want to run Nemotron 3 Ultra 550B-A55B faster — or step up to bigger models? Find your Mac →This is an LLMCheck index estimate from its published two-term bandwidth model, not a measured run; the index labels it so everywhere it appears. The bandwidth formula’s typical error for large MoEs is ±34% (mostly below the measured figure), against 70 measured runs of 18 models (how it is computed). Own this Mac? Submit a real run →
| Metric | Value |
|---|---|
| Tokens per second | estimated~12 tok/s |
| Provenance | estimate · how estimates are made |
| Quantization | Q4_K_M |
| Engine | llama.cpp |
| Figure dated | 2026-11 |
| Minimum RAM | 226 GB |
| Parameters | 550B MoE (55B active) |
| Chip bandwidth | 1228 GB/s |
Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (226 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.
| Speed | Quant | Engine | Mac RAM | Context | Source | Note |
|---|---|---|---|---|---|---|
| estimated12 tok/s | Q4_K_M | llama.cpp | 512 GB | — | LLMCheck estimator | — |
Ollama — the index has not verified an Ollama tag for Nemotron 3 Ultra 550B-A55B, so it doesn’t print one (a guessed tag fails with “pull model manifest: file does not exist”). Search the Ollama library →
MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:
Downloads: Hugging Face repo → · Hugging Face model card →
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
NVIDIA's OpenMDW-licensed 550B hybrid Mamba-Transformer MoE (55B active, 3 Jun 2026), 1M context; a catalog gap until this update. Card: SWE-bench Verified 70.7, Terminal-Bench 2.1 56.4, GPQA Diamond 87.0. Unsloth's UD-IQ3_XXS GGUF is 223 GB (a 256 GB Mac Studio, tight) and UD-Q3_K_M 274 GB; llama.cpp runs its nemotron_h architecture, but no Mac speed has been published.
OpenMDW licence · 550B MoE · 1000K context · LLMCheck capability 42/50 · see its leaderboard rank →
Estimated, not measured: the index’s minimum for Nemotron 3 Ultra 550B-A55B (226 GB — the weights at the quant that fits, plus ~2 GB) plus the KV cache for that many tokens, computed from its config.json. hybrid Mamba-2: attention on 12 of 108 layers; Mamba layers keep a constant state. A 16-bit KV cache is the default in llama.cpp, Ollama, LM Studio and mlx-lm; a q8 cache halves the KV part. Coding agents hold 64K tokens or more. Runtimes also add a buffer that grows with context, so leave a few GB spare. macOS lets the GPU use only part of a Mac’s memory by default (figures for an M5 Ultra Mac, which runs macOS 26 or later): “fits” means within the GPU memory a Mac of that tier can use with the limit raised, a tier tagged raise GPU limit fits only after sudo sysctl iogpu.wired_limit_mb raises it (the tooltip has the exact command), and the last column is the smallest Mac memory size whose default limit holds it (the GPU memory limit).
| Context | KV cache (16-bit) | RAM needed | RAM, q8 KV | Smallest tier that fits | Within the default GPU limit |
|---|---|---|---|---|---|
| 8K | ~0.1 GB | ~226.1 GB | ~226.0 GB | 512 GB Mac | |
| 32K | ~0.4 GB | ~226.4 GB | ~226.2 GB | 512 GB Mac | |
| 64K (coding-agent context) | ~0.8 GB | ~226.8 GB | ~226.4 GB | 512 GB Mac | |
| 128K | ~1.6 GB | ~227.6 GB | ~226.8 GB | 512 GB Mac |
Nemotron 3 Ultra 550B-A55B needs about 226 GB of unified memory. These Apple Silicon Macs have enough to run it. Apple builds the higher-memory configurations to order; Amazon does not stock them, so the used option links Amazon Renewed listings.
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.
See how Nemotron 3 Ultra 550B-A55B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard