AI tool comparison
Trinity-Large-Thinking 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.
Open Source Models
Trinity-Large-Thinking
399B open MoE reasoning model that's 96% cheaper than Claude Opus
75%
Panel ship
—
Community
Free
Entry
Trinity-Large-Thinking is a 399-billion-parameter open mixture-of-experts (MoE) reasoning model from Arcee AI, released under Apache 2.0. It's designed specifically for long-horizon multi-turn tool use and autonomous agentic tasks — thinking before responding with an explicit reasoning chain. The model ranked #2 on PinchBench (behind only Claude Opus 4.6) while costing $0.90/M output tokens via the Arcee API — roughly 96% cheaper than Opus. The full weights are freely downloadable from Hugging Face, making it one of the most capable openly-downloadable models available anywhere. Architecturally it draws on MoE efficiency to activate only a fraction of parameters per forward pass, enabling the massive 399B count without proportional compute cost. For teams building production agents that need serious reasoning but can't afford closed-model pricing at scale, Trinity-Large-Thinking is the most compelling open alternative that's appeared in a long time.
Open Source Models
Ternary Bonsai
1.58-bit LLMs that run at 82 tok/s on M4 Pro and on your iPhone
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.
Reviewer scorecard
“Near-Opus-level reasoning at $0.90/M tokens is the pricing inflection I've been waiting for. Apache 2.0 weights mean I can self-host for compliance-sensitive use cases. Already benchmarking it as a drop-in for my agent evaluation pipeline.”
“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.”
“Preview weights and PinchBench rankings tell part of the story — real-world agentic performance on messy production tasks is another matter. Arcee AI isn't Anthropic or Google; sustaining a 399B model with quality ongoing RLHF is expensive and the preview label is a yellow flag.”
“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.”
“A US-built, Apache-licensed frontier reasoning model competitive with closed offerings fundamentally changes the open-source AI landscape. The talent and capital required to do this was thought to only exist at the biggest labs. Arcee just proved otherwise.”
“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.”
“The thinking chain output is remarkably coherent for creative briefs and long-form narrative planning. At this price point I can run draft-then-refine pipelines at scale without budget anxiety. A genuine Ship for creative workflows.”
“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.