Qwen2.5-0.5B
A lightweight small-parameter large language model in Alibaba's Tongyi Qianwen series, with a parameter scale of 0.5B, suited to fine-tuning and inference experiments in resource-constrained environments.
Timeline (last 90 days)
In the 16-concurrency, 256-token-output test, Gemma 4 E2B achieves an output speed of 1887 tokens/second, and the models faster than it include Qwen2.5-0.5B (4176, 2.21x), Qwen3-0.6B (3210, 1.70x), Qwen2.5-1.5B (2780, 1.47x), and Qwen3-1.7B (2049, 1.09x).
Candidate small models include SmolLM2 (135M and 360M), Gemma 3 270M, LFM2.5-350M, Qwen2.5-0.5B, and Qwen3-0.6B, all of which have ONNX browser builds.
In Nodus's pilot on October 11, 2026, using a Qwen2.5-0.5B model running the same recipe on a single NVIDIA L4, supervised fine-tuning cost 67% less than Modal and continued pretraining cost 42.5% less; after counting one failed attempt, the fine-tuning savings dropped to 24.7%.
On Qwen2.5-0.5B, OAL reduces the relative mean squared error of frozen attention outputs by approximately 8.9% compared to DiJiang.
All Facts (3)
In the 16-concurrency, 256-token-output test, Gemma 4 E2B achieves an output speed of 1887 tokens/second, and the models faster than it include Qwen2.5-0.5B (4176, 2.21x), Qwen3-0.6B (3210, 1.70x), Qwen2.5-1.5B (2780, 1.47x), and Qwen3-1.7B (2049, 1.09x).
50%UnverifiedCandidate small models include SmolLM2 (135M and 360M), Gemma 3 270M, LFM2.5-350M, Qwen2.5-0.5B, and Qwen3-0.6B, all of which have ONNX browser builds.
50%UnverifiedOn Qwen2.5-0.5B, OAL reduces the relative mean squared error of frozen attention outputs by approximately 8.9% compared to DiJiang.
50%