Qwen2.5 2B runs on phones with 1GB RAM; MMLU jumps to 54.8
alexcovo_eth · x · 2026-08-17
The distilled Qwen2.5 2B model runs on devices with just 1GB RAM (Q4KM). It features 262k context, function calling, and full-parameter SFT. Benchmarks show significant gains: MMLU CoT increased from 28.3 to 54.8, and GSM8K from 33 to 64.
More from Models
- 8 frontier LLMs benchmarked on 50 tasks across 10 dimensions over two days — lxfater · 2026-08-17
- GLM 5.3 Shows Strong Cybersecurity Capabilities, Low Cost Benefits Defensive Ops — ccerrato147 · 2026-08-17
- GLM5.2 struggles with wrong language token sampling on non-Chinese/English prompts — kalomaze · 2026-08-17
- GLM-5.3 review: Cleaner code and consistent long-horizon performance — khademinori · 2026-08-17
- Test: Qwen 3.8 27B Outperforms GPT-5.6 Sol in Complex SVG Animation Tasks — Lirezh · 2026-08-17
- Seedance 2.5 Tops Multi-Image-to-Video Benchmark with Elo 1400 — rohanpaul_ai · 2026-08-17