Same model, same Q4_K_M label: 5.02, 5.07 and 5.27 bits per weight

Related Discussions

Found 5 related stories in 684.1ms across 14,015 title embeddings via pgvector HNSW

• Xiaomi releases MiMo-v2.5 Family weights with strong coding and agent benchmarks steveharing1 · 19 pts · April 28, 2026 · 51% similar
• Show HN: Quant Picker – which GGUF file fits your model and machine ermantrout · 15 pts · June 13, 2026 · 47% similar
• Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distribution FranckDernoncou · 34 pts · May 15, 2026 · 45% similar
• Qwen3.5 Fine-Tuning Guide bilsbie · 311 pts · March 04, 2026 · 44% similar
• GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2 oshrimpton · 53 pts · June 19, 2026 · 44% similar