AI article
Small Apache-2.0 Models Against Gemma 4 E2B on One TPU v5e: Which Ones Keep Up?
Community description: Fourteen Apache-2.0 and MIT open-weight models that fit one TPU v5e chip, served one after another through vLLM on the same pinned image and scored on GSM8K and BFCL against Gemma 4 E2B. Qwen3-4B matches Gemma's accuracy at 0.57x its output, SmolLM3-3B and Granite 3.3 2B match it on tool calls, and Gemma keeps the lead on long prompts.
Dev.to | Oct 13, 2026 | xbill
Automated excerpt
Qwen3-4B matches Gemma on both accuracy tests at 0. 57x the output. With long prompts, Gemma stays ahead of every model of comparable accuracy. Five models are level with Gemma on BFCL tool calls, down to Qwen2. 5-1. 5B.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.