The LLMCheck index estimates Hy4 preview at ~14 tok/s on an M5 Ultra at Q4_K_M, a figure from its published bandwidth model, not a measured run. It needs about 292 GB of unified memory. It is Tencent's 770B mixture-of-experts model (49B active), released under the Apache 2.0 licence.
llama.cpp has its hy_v4 architecture from b10813, but it was validated only on CUDA and no Mac run has been published; MLX needs an unmerged mlx-lm branch.
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~14 tok/s |
| Provenance | estimate · how estimates are made |
| Quantization | Q4_K_M |
| Engine | llama.cpp |
| Figure dated | 2026-11 |
| Minimum RAM | 292 GB |
| Parameters | 770B MoE (49B 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 (292 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 |
|---|---|---|---|---|---|---|
| estimated14 tok/s | Q4_K_M | llama.cpp | 512 GB | — | LLMCheck estimator | — |
Ollama — the index has not verified an Ollama tag for Hy4 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.
Tencent's Apache 2.0 770B MoE preview (49B active, 27 Aug 2026), 1M context; the card calls it an early version with known issues. Vendor appendix: SWE-bench Pro 65.7, GPQA Diamond 92.3. Its smallest GGUF of about 3 bits per weight (6block's Q2_K) is 289.5 GB, so it needs a 512 GB Mac Studio.
Apache 2.0 licence · 770B MoE · 1000K context · LLMCheck capability 48/50 · see its leaderboard rank →
Estimated, not measured: the index’s minimum for Hy4 preview (292 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 all 78 layers (kv_lora_rank 512 + rope 64); DSA lightning-indexer keys (index_head_dim per layer) not counted; runtimes that expand MLA to per-head K/V use far more. 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 | ~0.7 GB | ~292.4 GB | ~292.2 GB | 512 GB Mac | |
| 32K | ~2.9 GB | ~294.6 GB | ~293.3 GB | 512 GB Mac | |
| 64K (coding-agent context) | ~5.9 GB | ~297.5 GB | ~294.8 GB | 512 GB Mac | |
| 128K | ~11.8 GB | ~303.4 GB | ~297.7 GB | 512 GB Mac |
Hy4 preview needs about 292 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 Hy4 preview stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard