FIT-GGUF 为 MiniCPM5-2B 带来可控体积的混合精度量化
用 FIT-GGUF 给 MiniCPM5-2B 做了 4 个混合精度量化版，1.14 到 1.46 GiB，还能自定目标体积，比固定 Q4/Q5 灵活多了。
开发者 Scorp1o_117 用 FIT-GGUF 工具为 MiniCPM5-2B 制作了多个 GGUF 量化版本。用户可以设定目标文件体积或保真度等级，工具会自动为不同张量分配精度，再预测、生成并校验最终 GGUF 文件。本次共发布 4 个版本，体积从约 1.14 GiB 到约 1.46 GiB，并提供 Quality、Balanced、Compact、Mini 四种预设。评测采用 KL Divergence 和 Same-top 指标，生成文件的体积与预测目标一致。这种方式让模型适配不同内存和部署条件，不必再局限于单一的 Q4/Q5 量化预设。
🚀 FIT-GGUF brings controllable-size mixed-precision quantization to MiniCPM5-2B Developer @Scorp1o_117 used FIT-GGUF to build MiniCPM5-2B GGUF variants around specific size and quality targets. Instead of choosing a fixed quantization preset, you can set a target file size or fidelity tier, and FIT-GGUF automatically decides how much precision to allocate to different tensors—then predicts, generates, and verifies the final GGUF.
✨ What’s included 🧠 Tensor-level mixed-precision quantization 📦 Four MiniCPM5-2B builds from ~1.14 GiB to ~1.46 GiB 🎯 Quality / Balanced / Compact / Mini presets 📊 KL Divergence and Same-top evaluation ✅ Generated file sizes matched the predicted targets
A nice example of how MiniCPM5-2B can be tuned for different memory and deployment constraints, without being locked into a single Q4/Q5-style quantization preset.
Check out FIT-GGUF and try building a MiniCPM5-2B variant that fits your own device budget.
🤗Model: https://t.co/WL3o7jLA1M https://t.co/FZOMTZh3tS
