Ternary Bonsai 2 27B runs at 13 tok/s (13.3 as recorded) on a 32 GB M6, a community run reported by omlx.ai (MLX, Ternary, 4k context). It needs about 9 GB of unified memory. It is Prism ML's 27.36B dense model, released under the Apache 2.0 licence.
Want to run Ternary Bonsai 2 27B 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 | community13 tok/s |
| Provenance | community run · omlx.ai |
| Quantization | Ternary |
| Engine | MLX |
| Context | 4k |
| Figure dated | 2026-10-23 |
| Minimum RAM | 9 GB |
| Parameters | 27.36B |
| Chip bandwidth | 170 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 (9 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 |
|---|---|---|---|---|---|---|
| community13.3 tok/s | Ternary | MLX | 32 GB | 4k | omlx.ai | 12-core GPU. oMLX v0.7.1rc1, MTP/DFlash off; prism-ml Ternary-Bonsai-2-27B-mlx-2bit, so it does not anchor; 13.9 GB peak. 10.5 tok/s at 16k.; not used to anchor estimates |
Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-10-24:
MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:
Downloads: Ollama page → · model card →
The 13 tok/s figure above came from MLX at Ternary; 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.
Prism ML's ternary (1.58-bit) rebuild of Qwen3.8-27B (Sep 2026, Apache 2.0): ~7 GB, image input, 262K context. It keeps 98% of the base model's average on Prism's 14-benchmark suite but drops on agentic coding (SWE-bench Verified 60.8 vs 80.6 on Prism's scaffold). Ternary decoding is kernel-bound, so the index quotes measured figures only: the vendor's 46.8 tok/s on an M5 Max and 28.1 on an M5 Pro (PrismML llama.cpp fork, PQ2_0), and community runs of 34.5 on an M4 Max and 20.5 on an M4 Pro (same fork) and 43.4 on an M5 Max and 13.3 on an M6 (MLX ternary pack, oMLX); Ollama's bonsai-2:27b ships the 8.3 GB Q2_0 pack.
Apache 2.0 licence · 27.36B · 262K context · LLMCheck capability 37/50 · see its leaderboard rank →
Ternary Bonsai 2 27B needs about 9 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
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 Ternary Bonsai 2 27B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard