Ternary Bonsai 2 9B runs at 40 tok/s (40.2 as recorded) on a 16 GB M6, a community run reported by omlx.ai (MLX, Ternary, 4k context). It needs about 5 GB of unified memory. It is Prism ML's 9.41B dense model, released under the Apache 2.0 licence.
Want to run Ternary Bonsai 2 9B 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 | community40 tok/s |
| Provenance | community run · omlx.ai |
| Quantization | Ternary |
| Engine | MLX |
| Context | 4k |
| Figure dated | 2026-10-21 |
| Minimum RAM | 5 GB |
| Parameters | 9.41B |
| 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 (5 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 |
|---|---|---|---|---|---|---|
| community40.2 tok/s | Ternary | MLX | 16 GB | 4k | omlx.ai | The 16 GB Mac mini M6 is the binned 153 GB/s part. oMLX v0.7.0rc1, MTP/DFlash off; prism-ml Ternary-Bonsai-2-9B-mlx-2bit; 6.3 GB peak. 31.7 tok/s at 16k.; binned GPU |
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 40 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.
| Chip | Speed | Quant | Engine | Bandwidth |
|---|---|---|---|---|
| M5 Pro | sourced77 tok/s | PQ2_0 | llama.cpp | 307 GB/s |
Prism ML's ternary Qwen3.5-9B with vision (15 Oct 2026, Apache 2.0): 2.4 GB plus a 0.6 GB vision projector, 262K context. Ternary decoding is kernel-bound, so the index quotes measured figures only: 76.5 tok/s on an M5 Pro (vendor, PrismML llama.cpp fork, PQ2_0, tg128) and 40.2 on a 16 GB Mac mini M6 (community, MLX ternary pack, oMLX). Ollama's bonsai-2:9b (3.2 GB) uses the Q2_0 pack.
Apache 2.0 licence · 9.41B · 262K context · LLMCheck capability 16/50 · see its leaderboard rank →
Ternary Bonsai 2 9B needs about 5 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 9B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard