Muse Glimmer 30B runs at 27 tok/s on a 64 GB M5 Max, a published figure reported by huggingface.co (MLX, Q4_K_M). It needs about 18 GB of unified memory. It is Meta's 30B dense model, released under the Apache 2.0 licence.
Want to run Muse Glimmer 30B faster — or step up to bigger models? Find your Mac →This is a published figure: 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 | sourced27 tok/s |
| Provenance | published figure · huggingface.co |
| Quantization | Q4_K_M |
| Engine | MLX |
| Time to first token | 0.4s |
| Figure dated | 2026-08 |
| Minimum RAM | 18 GB |
| Parameters | 30B |
| 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 (18 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 |
|---|---|---|---|---|---|---|
| sourced27 tok/s | Q4_K_M | MLX | 64 GB | — | huggingface.co | — |
Ollama — the index has not verified an Ollama tag for Muse Glimmer 30B, 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 27 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.
Meta's 30B model, ~27 tok/s on M5 Max. Apache 2.0 license, LLMCheck capability 42/50.
Apache 2.0 licence · 30B · 131K context · LLMCheck capability 42/50 · see its leaderboard rank →
Estimated, not measured: the index’s minimum for Muse Glimmer 30B (18 GB — the weights at the quant that fits, plus ~2 GB) plus the KV cache for that many tokens, computed from its config.json. 13 full layers + 39 sliding-window layers (window 2048). 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 | ~18.1 GB | ~18.0 GB | 24 GB Mac raise GPU limit | 32 GB Mac |
| 32K | ~0.5 GB | ~18.4 GB | ~18.2 GB | 24 GB Mac raise GPU limit | 32 GB Mac |
| 64K (coding-agent context) | ~1.0 GB | ~18.8 GB | ~18.4 GB | 24 GB Mac raise GPU limit | 32 GB Mac |
| 128K | ~1.8 GB | ~19.7 GB | ~18.8 GB | 24 GB Mac raise GPU limit | 32 GB Mac |
Muse Glimmer 30B needs about 18 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.
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 Muse Glimmer 30B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard