Compare/MiniMax M2.7 vs Ternary Bonsai

AI tool comparison

MiniMax M2.7 vs Ternary Bonsai

Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.

M

AI Models

MiniMax M2.7

230B open-weights MoE reasoning model built for coding and agentic workflows

Mixed

50%

Panel ship

Community

Free

Entry

MiniMax M2.7 is a 230B-parameter Mixture-of-Experts reasoning model released as open weights in April 2026. Only 10 billion parameters activate per token (8 of 256 experts), which enables frontier-level performance at significantly lower inference cost and latency than dense models of comparable quality. The context window stretches to 204,800 tokens — roughly 307 pages of text — with strong performance on long-horizon agentic tasks. M2.7 is purpose-built for tool-using agents and coding workflows. It scored 50 on the Artificial Analysis Intelligence Index, placing it among the top open-weight models globally. Weights landed on Hugging Face simultaneously with an API launch and the open-sourcing of OpenRoom, MiniMax's interactive agent orchestration system — a rare move that gives developers the full stack from model to agent runtime. MiniMax is a Shanghai-based AI company that has been quietly iterating through M1, M2, M2.5, and now M2.7 with consistent improvements. The M2.7 release represents a notable capability jump in the MoE open-weights space, particularly for developers who need a locally deployable model that can handle complex multi-step agent tasks without calling a paid API.

T

Open Source Models

Ternary Bonsai

1.58-bit LLMs that run at 82 tok/s on M4 Pro and on your iPhone

Ship

75%

Panel ship

Community

Free

Entry

PrismML's Ternary Bonsai is a family of aggressively quantized language models that take the BitNet concept to its logical extreme. Each weight is constrained to one of three values — {-1, 0, +1} — with a shared FP16 scale factor per 128-weight group. No higher-precision escape hatches, no hybrid layers. The result is a 9x reduction in memory footprint versus standard 16-bit models. The numbers are striking: the 8B model fits in 1.75 GB and hits 82 tokens per second on an M4 Pro. More impressively, it runs at 27 tokens per second on an iPhone 17 Pro Max — fast enough for real-time conversation on-device. The 8B variant scores 75.5 average across standard benchmarks, outperforming many models that are 9-10x larger. The 4B and 1.7B variants push further into mobile-optimized territory. All three models are released under the Apache 2.0 license, available on Hugging Face and GitHub, and integrated into the Locally AI iOS app for immediate on-device deployment. For developers building privacy-sensitive applications or anyone tired of paying cloud inference costs, Ternary Bonsai offers a compelling on-device alternative that doesn't require a beefy GPU.

Decision
MiniMax M2.7
Ternary Bonsai
Panel verdict
Mixed · 2 ship / 2 skip
Ship · 3 ship / 1 skip
Community
No community votes yet
No community votes yet
Pricing
Free / Open Weights (self-host) / API via MiniMax
Open Source / Apache 2.0 / Free
Best for
230B open-weights MoE reasoning model built for coding and agentic workflows
1.58-bit LLMs that run at 82 tok/s on M4 Pro and on your iPhone
Category
AI Models
Open Source Models

Reviewer scorecard

Builder
80/100 · ship

Only 10B active params with 230B total is a sweet spot — you get near-frontier quality with manageable inference costs. The open-sourced OpenRoom agent runtime alongside the weights makes this a production-ready stack, not just a model drop.

80/100 · ship

82 tokens per second on M4 Pro in 1.75 GB is a genuinely impressive engineering achievement. For local tooling, code assistants, or any latency-sensitive workload where I don't want cloud round-trips, this hits a sweet spot that larger quantized models miss. Apache 2.0 means I can embed it in commercial apps without legal headaches.

Skeptic
45/100 · skip

MiniMax is still less battle-tested than Qwen or Llama in community tooling. 230B total weights still require serious hardware even with MoE efficiency. And the version cadence (M2 to M2.5 to M2.7) suggests rapid deprecation cycles.

45/100 · skip

A 75.5 benchmark average sounds good until you compare it against 8B models quantized with GGUF Q8 — which score similarly and have years of tooling, community support, and production deployments behind them. The 9x memory savings matter on constrained devices but less so on any machine with 16GB+ RAM. Niche but real use case.

Futurist
80/100 · ship

The combination of open-source agent runtime plus frontier-adjacent open weights is exactly the stack needed to enable truly sovereign AI deployments. MiniMax is quietly building one of the most complete open-source AI stacks in the world.

80/100 · ship

On-device AI at 27 tokens per second on a phone is the inflection point that makes LLMs a platform primitive rather than a cloud service. Once inference is this cheap and fast on commodity hardware, the entire economic model of AI-as-API-call collapses. Ternary quantization is an early signal of where efficiency research is heading.

Creator
45/100 · skip

For pure creative tasks, the MoE trade-offs in consistency aren't ideal. Locally running a 230B model is still not practical for most creator workflows without dedicated GPU infrastructure.

80/100 · ship

The prospect of running a capable LLM entirely on my iPhone without sending any data to a server is genuinely exciting for creative work with sensitive material. Drafting, editing, and ideation without a cloud subscription or privacy concerns — I'd pay for that, and here it's free.

Weekly AI Tool Verdicts

Get the next comparison in your inbox

New AI tools ship daily. We compare them before you waste an afternoon.

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later