GLM 5.2 runs at 15 tok/s on a 512 GB M3 Ultra, a community run reported by kingy.ai (MLX, Q4_K_M). It needs about 256 GB of unified memory. It is Zhipu AI's 753B mixture-of-experts model (40B active), released under the MIT licence.
Want to run GLM 5.2 faster — or step up to bigger models? Find your Mac →This is a community run: a real run, reported by its source and linked below. The index records it as given and never adjusts it.
| Metric | Value |
|---|---|
| Tokens per second | community15 tok/s |
| Provenance | community run · kingy.ai |
| Quantization | Q4_K_M |
| Engine | MLX |
| Time to first token | 2.0s |
| Figure dated | 2026-07 |
| Minimum RAM | 256 GB |
| Parameters | 753B MoE (40B active) |
| Chip bandwidth | 819 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 (256 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 |
|---|---|---|---|---|---|---|
| community22 tok/s | IQ1_S | LM Studio | 256 GB | — | codersera.com | — |
| community15 tok/s | Q4_K_M | MLX | 512 GB | — | kingy.ai | — |
Ollama — the index has not verified an Ollama tag for GLM 5.2, 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: Search the Ollama library → · Hugging Face model card →
The 15 tok/s figure above came from MLX at Q4_K_M; other runtimes and quants run at different speeds.
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
| Chip | Speed | Quant | Engine | Bandwidth |
|---|---|---|---|---|
| M5 Ultra | estimated22 tok/s | Q4_K_M | llama.cpp | 1228 GB/s |
Zhipu AI's open-frontier flagship — leads open weights on SWE-Bench Pro (62–68.5% depending on harness). MIT, 753B-A40B MoE. Server-class; community 1-bit quants run on a 256 GB M3 Ultra. On a 64 GB Mac, use GLM-4.5-Air.
MIT licence · 753B MoE · 256K context · LLMCheck capability 50/50 · see its leaderboard rank →
Estimated, not measured: the index’s minimum for GLM 5.2 (256 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 M3 Ultra Mac on macOS 15, the lower default; macOS 26 allows more): “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 | ~256.4 GB | ~256.2 GB | 512 GB Mac | |
| 32K | ~2.9 GB | ~258.6 GB | ~257.3 GB | 512 GB Mac | |
| 64K (coding-agent context) | ~5.9 GB | ~261.5 GB | ~258.8 GB | 512 GB Mac | |
| 128K | ~11.8 GB | ~267.4 GB | ~261.7 GB | 512 GB Mac |
GLM 5.2 needs about 256 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 GLM 5.2 stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard