AI tool comparison
Qwen3.6-Plus 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.
AI Models
Qwen3.6-Plus
The agentic coding model beating Claude Opus 4.5 — free on OpenRouter
75%
Panel ship
—
Community
Free
Entry
Qwen3.6-Plus is Alibaba's latest frontier model, built specifically for agentic real-world tasks with a particular emphasis on software engineering. Released in preview on OpenRouter as a free tier, it scores 61.6 on Terminal-Bench 2.0, edging past Claude Opus 4.5 (59.3), while running at roughly 3x the speed. It supports a 1M token context window with 65K output tokens — larger than most competitors. Under the hood, Qwen3.6-Plus is a sparse mixture-of-experts architecture, activating a fraction of its parameters per forward pass for efficiency. It supports both text and multimodal inputs, and the API supports tool use natively — making it well-suited for agent loops. The free preview is positioned as a direct challenge to OpenAI and Anthropic in the agentic coding space. The timing is notable: released the same week as Google Gemma 4 and Cursor 3, signaling an industry-wide pivot from autocomplete to full autonomous agents. With free preview access already expiring, Alibaba is clearly using the buzz from benchmark dominance to drive early adoption at the API tier.
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
“The Terminal-Bench numbers don't lie — this thing completes agentic coding tasks better than Opus at a fraction of the cost. The 1M context window means I can throw an entire monorepo at it. Free preview while it lasts is a no-brainer for any dev working on agent pipelines.”
“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.”
“Benchmark performance on Terminal-Bench doesn't always translate to real-world reliability. Alibaba's track record on model longevity and API uptime is spottier than Anthropic's or OpenAI's. The free preview ending today is also a classic bait-and-switch move — the real question is what the paid tier costs.”
“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.”
“We're seeing the first real multi-model agent race, and Qwen3.6-Plus is the opening shot from China. The combination of 1M context, agentic optimization, and benchmark-beating performance signals that the era of Western AI dominance in coding agents may be over. This reshapes the market.”
“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.”
“For automation-heavy creative workflows — building tools, scraping, image pipelines — having a faster, cheaper frontier model with giant context is genuinely useful. I can run whole project contexts through it without hitting limits. The free preview makes it a zero-cost experiment.”
“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.