AI tool comparison
Qwen3 Family 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.
Foundation Models
Qwen3 Family
Alibaba's full model family: 0.6B to 235B with thinking modes
75%
Panel ship
—
Community
Paid
Entry
Alibaba's Qwen team released the full Qwen3 model family this week — 8 models ranging from 0.6B to 235B parameters, spanning both dense and Mixture-of-Experts (MoE) architectures. The headline model is Qwen3-235B-A22B, a 235B MoE that activates 22B parameters per token and matches GPT-4.1 on coding and math benchmarks while running at a fraction of the cost. All Qwen3 models feature switchable "thinking modes" — a built-in chain-of-thought toggle that can be enabled or disabled per request. This eliminates the need for separate reasoning vs. instruct variants, letting developers trade latency for accuracy dynamically. All models are released under Apache 2.0, with weights available on Hugging Face and ModelScope. The smaller models are competitive at their size class: Qwen3-4B reportedly matches Qwen2.5-72B-Instruct on several benchmarks, and the 0.6B model is designed to run efficiently on embedded and edge devices. The release also introduces a new multilingual benchmark covering 119 languages, on which the Qwen3 family sets new state-of-the-art scores for open-weights models.
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
“Apache 2.0 on a 235B model that matches GPT-4.1 is the most impactful open-source release of the quarter. The dynamic thinking mode toggle is exactly what production systems need — you don't always want a 30-second reasoning chain on every request.”
“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.”
“Alibaba's benchmark methodology has been questioned before. The 'matches GPT-4.1' claim needs independent validation on real tasks. Also, while Apache 2.0 is permissive, enterprise legal teams will still scrutinize models from Chinese companies for compliance reasons.”
“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.”
“Eight models with consistent APIs, multilingual coverage, and open weights — this is what a real AI platform looks like. Alibaba is building a global alternative to OpenAI's stack, and the quality gap is closing faster than anyone expected two years ago.”
“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 multilingual benchmark improvements are huge for global content teams. I tested Qwen3-7B on Japanese marketing copy and it handled tone and register better than anything at this size class. For small teams creating content in non-English markets, this is a serious unlock.”
“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.