Yes: Nemotron 3.5 Super VL 120B-A12B runs on 12 of the 54 Macs in the LLMCheck index. It needs about 72 GB at a 4K context, 73 GB at 64K. Smallest current Mac: Mac Studio M5 Ultra 96 GB; cheapest at 15+ tok/s: Mac Studio M5 Max 128 GB, $5,099. Best measured figure: 74.3 tok/s on an M5 Ultra (community).
One row per Mac configuration, grouped by product line. The build is the one each speed is for; the context column is the longest prompt that fits inside macOS’s default GPU memory limit with a 16-bit KV cache (“raised” where the limit has to be raised first; “full” when the whole window fits). Speeds are decode tok/s from the LLMCheck index, each with its provenance mark. For large mixture-of-experts models (over 40B total), the formula’s typical error is about 34% (the median gap to 70 measured plain-decode runs; it tends to undershoot (median −33%), and an estimate scaled from the model’s own measured run is usually closer; method).
| Mac | Verdict | Build | Speed | Max context | Model page |
|---|---|---|---|---|---|
| MacBook Air | |||||
| MacBook Air M5 16 GB | Doesn't fit | — | — | — | — |
| MacBook Air M5 24 GB | Doesn't fit | — | — | — | — |
| MacBook Air M5 32 GB | Doesn't fit | — | — | — | — |
| MacBook Air M1 8 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M4 16 GB used | Doesn't fit | — | — | — | — |
| MacBook Air M2 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M3 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M1 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M4 24 GB used | Doesn't fit | — | — | — | — |
| MacBook Air M2 24 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M3 24 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Pro | |||||
| MacBook Pro M6 16 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 24 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M6 24 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M6 32 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 48 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Max 64 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 64 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Max 128 GB | Runs | Q4_0 | community36 tok/s | 1M (full) | M5 Max page |
| MacBook Pro M3 Max 64 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Pro M3 Max 128 GB refurb | Runs | Q4_K_M | estimated36 tok/s | 1M (full) | — |
| Mac mini | |||||
| Mac mini M6 16 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 24 GB | Doesn't fit | — | — | — | — |
| Mac mini M6 24 GB | Doesn't fit | — | — | — | — |
| Mac mini M6 32 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 48 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 64 GB | Doesn't fit | — | — | — | — |
| Mac mini M2 Pro 16 GB refurb | Doesn't fit | — | — | — | — |
| Mac mini M4 16 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 24 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 24 GB used | Doesn't fit | — | — | — | — |
| Mac mini M2 Pro 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 48 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 64 GB used | Doesn't fit | — | — | — | — |
| iMac | |||||
| iMac M6 16 GB | Doesn't fit | — | — | — | — |
| iMac M6 24 GB | Doesn't fit | — | — | — | — |
| iMac M6 32 GB | Doesn't fit | — | — | — | — |
| Mac Studio | |||||
| Mac Studio M5 Max 36 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 48 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 64 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Ultra 96 GB | Runs | 4-bit | community74 tok/s | 690K | M5 Ultra page |
| Mac Studio M5 Max 128 GB | Runs | Q4_0 | community36 tok/s | 1M (full) | M5 Max page |
| Mac Studio M5 Ultra 256 GB | Runs | 4-bit | community74 tok/s | 1M (full) | M5 Ultra page |
| Mac Studio M5 Ultra 512 GB | Runs | 4-bit | community74 tok/s | 1M (full) | M5 Ultra page |
| Mac Studio M2 Max 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 64 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M4 Max 64 GB used | Doesn't fit | — | — | — | — |
| Mac Studio M2 Max 64 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 128 GB refurb | Runs | Q4_K_M | estimated58 tok/s | 1M (full) | — |
| Mac Studio M2 Ultra 128 GB refurb | Runs | Q4_K_M | estimated58 tok/s | 1M (full) | — |
| Mac Studio M4 Max 128 GB used | Runs | 4-bit | community51 tok/s | 1M (full) | M4 Max page |
| Mac Studio M2 Ultra 192 GB refurb | Runs | Q4_K_M | estimated58 tok/s | 1M (full) | — |
| Mac Studio M3 Ultra 256 GB used | Runs | Q4_K_M | estimated59 tok/s | 1M (full) | — |
| Mac Studio M3 Ultra 512 GB refurb | Runs | Q4_K_M | estimated59 tok/s | 1M (full) | — |
Context memory is computed from its config.json (hybrid Mamba-2: attention on 8 of 88 layers; Mamba layers keep a constant state): about 0.5 GB of 16-bit KV cache at 64K tokens. A q8 cache (llama.cpp -ctk q8_0 -ctv q8_0, Ollama OLLAMA_KV_CACHE_TYPE=q8_0) halves that part. Runtimes also grow a compute buffer with context, so a fit within about 1 GB of the limit is optimistic.
macOS lets the GPU use only part of unified memory by default. Nemotron 3.5 Super VL 120B-A12B fits inside that default limit on every Mac it fits at all, so no Mac in the table needs it raised at a short context. Long contexts may still need it: the context column already uses each Mac’s default limit.
Weights are 120B parameters at each format’s effective size (the index’s GB-per-billion table), plus about 2 GB for the runtime and a short context; longer contexts add the KV cache computed from the model’s config.json at 16 bits. It is a mixture-of-experts model: all 120B parameters sit in memory although only 12B are read per token. The first row is the catalog’s own figure (about 72 GB at a 4K context), the one every verdict on this page uses. “Smallest Mac” is the smallest memory size among the Macs Apple sells new that holds it at a 4K context inside that Mac’s default GPU limit. Estimates, not measurements.
| Build | Weights | RAM at 4K | at 32K | at 64K | Smallest Mac |
|---|---|---|---|---|---|
| As catalogued | — | 72 GB | 72 GB | 73 GB | 96 GB |
| Q2_K | 40.8 GB | 43 GB | 43 GB | 43 GB | 64 GB |
| Q3_K_M | 58.8 GB | 61 GB | 61 GB | 61 GB | 96 GB |
| Q4_K_M | 68.4 GB | 70 GB | 71 GB | 71 GB | 96 GB |
| Q5_K_M | 85.2 GB | 87 GB | 87 GB | 88 GB | 128 GB |
| Q6_K | 98.4 GB | 100 GB | 101 GB | 101 GB | 128 GB |
| Q8_0 | 127.2 GB | 129 GB | 129 GB | 130 GB | 256 GB |
| F16 | 240.0 GB | 242 GB | 242 GB | 243 GB | 512 GB |
Every published (filled square) and community (hollow circle) run the index holds for Nemotron 3.5 Super VL 120B-A12B: 0 published, 6 community, each linked to its source. LLMCheck runs no tests of its own. One row is one measurement session; on each chip the table above shows the lower median of the eligible runs (plain decode at 5 bits or fewer), and a binned or “not an anchor” run is shown but never used as a reference.
| Chip | Runtime | Quant | Decode | Context | Date | Source |
|---|---|---|---|---|---|---|
| M5 Ultra | MLX | 4-bit | community74.3 tok/s | 1k | 2026-10-19 | omlx.ai |
| M5 Max | MLX | 4-bit | community51.8 tok/s | 512-token coding answers, median of 5 at T 0.6 | 2026-10-18 | github.com |
| M5 Max | MLX | 4-bit | community45.5 tok/s | 512-token coding answers, median of 5 at T 0.6 | 2026-10-18 | github.com |
| M5 Max | llama.cpp | Q4_0 | community35.9 tok/s | 512-token coding answers, median of 5 at T 0.6 | 2026-10-18 | github.com |
| M5 Max | MLX | NVFP4 | community30.6 tok/s | 160 generated tokens, greedy | 2026-10-16 | github.com |
| M4 Max | MLX | 4-bit | community50.8 tok/s | 1k | 2026-10-18 | omlx.ai |
The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 90 GB):
Prefer a window to a terminal? LM Studio downloads the same model with one click. · model card →
On the Mac Studio M5 Ultra (96 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is 74 tok/s (community run) at 4-bit; keep the context at or under 690K there, or use a q8 KV cache. Note: the nemotron-3.5-super:120b tag is about 90 GB, so it needs a 128 GB Mac; on 96 GB use a ~5-bit build after raising the GPU limit.
Step-by-step: the Ollama install guide.
Mac Studio M5 Ultra (96 GB) — smallest current Mac that runs it, $5,499 new (Apple list price, checked 2026-11-14), 74 tok/s (community run). For Ollama: the nemotron-3.5-super:120b tag is about 90 GB, so it needs a 128 GB Mac; on 96 GB use a ~5-bit build after raising the GPU limit. Mac Studio M5 Max (128 GB) — cheapest at 15+ tok/s, $5,099 new (Apple list price, checked 2026-11-14), 36 tok/s (community run). Amazon does not stock the Mac Studio M5 Ultra (96 GB): Apple builds it to order. Amazon does not stock the Mac Studio M5 Max (128 GB): Apple builds it to order.
Yes. Nemotron 3.5 Super VL 120B-A12B needs about 72 GB of unified memory at a short (4K-token) context, so it runs on 12 of the 54 Mac configurations in the LLMCheck index. The smallest Mac Apple sells new that runs it is the Mac Studio M5 Ultra (96 GB).
About 72 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 73 GB in total at 32K and 73 GB at 64K with the default 16-bit cache (about 73 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.
On an M5 Max, the chip the leaderboard quotes it on, the index figure is 36 tok/s (community run) at Q4_0. The best measured figure is 74.3 tok/s on an M5 Ultra 96 GB (community run, 4-bit). Every Mac’s figure is in the table on this page with its provenance: published, community run or estimated.
Among Macs Apple sells new, the Mac Studio M5 Max (128 GB), $5,099 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Nemotron 3.5 Super VL 120B-A12B, at 36 tok/s (community run).
No. On all 12 Mac configurations where Nemotron 3.5 Super VL 120B-A12B fits, it fits inside that Mac’s default GPU memory limit at a short context; only a long context on the smallest of them can push it over.
Q4_K_M (about 68 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 127 GB) is closer to full quality and needs a 256 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 59 and 41 GB at a quality cost. The index’s reference figure (36 tok/s on an M5 Max) is for its Q4_0 build.
Its own window is 1M tokens. At macOS’s default GPU limit, the Mac Studio M5 Ultra (96 GB) holds about 690K. The full window needs about 81 GB, which a 128 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.
LLMCheck. (2026). Can I run Nemotron 3.5 Super VL 120B-A12B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/nemotron-35-super-vl-120b-a12b/ (updated ). CC BY 4.0.