The LLMCheck index estimates dots3-note preview at ~28 tok/s on an M5 Max at 3.5 bpw, a figure from its published bandwidth model, not a measured run. It needs about 120 GB of unified memory. It is Xiaohongshu (RedNote)'s 280B mixture-of-experts model (16B active), released under the Apache 2.0 licence.
Want to run dots3-note preview 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~28 tok/s |
| Provenance | estimate · how estimates are made |
| Quantization | 3.5 bpw |
| Engine | llama.cpp |
| Figure dated | 2026-11 |
| Minimum RAM | 120 GB |
| Parameters | 280B MoE (16B active) |
| Chip bandwidth | 614 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 (120 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 |
|---|---|---|---|---|---|---|
| estimated28 tok/s | 3.5 bpw | llama.cpp | 128 GB | — | LLMCheck estimator | The build that sets the catalog's minimum RAM (120 GB; ggml-org's IQ3_XXS GGUF is 117.5 GB), costed at the 3.5 bits per weight that size implies. |
Ollama — the index has not verified an Ollama tag for dots3-note preview, 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.
Xiaohongshu (RedNote)'s Apache 2.0 280B MoE preview (16B active, 14 Aug 2026): text, image, video and audio in, 512K context. Vendor chart: SWE-bench Pro 61.0, Terminal-Bench 2.1 75.1 (harness not stated). bartowski's IQ3_XXS is 117.5 GB, so it needs a 128 GB Mac; upstream llama.cpp runs it from b10569 (vision and audio from b10580). No Mac speed has been published on a released build yet.
Apache 2.0 licence · 280B MoE · 512K context · LLMCheck capability 44/50 · see its leaderboard rank →
Estimated, not measured: the index’s minimum for dots3-note preview (120 GB — the weights at the quant that fits, plus ~2 GB) plus the KV cache for that many tokens, computed from its config.json. MLA on 13 full layers (512+64), latent MLA on 33 sliding layers (1024+64, window 513); DSA indexer keys not counted. 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 Max 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 | ~0.2 GB | ~120.1 GB | ~120.0 GB | 192–256 GB Mac | |
| 32K | ~0.5 GB | ~120.4 GB | ~120.2 GB | 192–256 GB Mac | |
| 64K (coding-agent context) | ~1.0 GB | ~120.9 GB | ~120.5 GB | 192–256 GB Mac | |
| 128K | ~2.0 GB | ~121.9 GB | ~121.0 GB | 192–256 GB Mac |
dots3-note preview needs about 120 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 dots3-note preview stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard