gemma 4 A4B 98e v7 coderx it GGUF GGUF quantizations of ManniX ITA/gemma 4 A4B 98e v7 coderx it. All quants made using imatrix with calibration data v5. The imatrix.dat used is included in this repo for reproducibility/audit; mmproj gemma4.gguf is the shared Gemma 4 SigLIP vision tower (untouched by pruning) for multimodal use. Quantizations — score, size & answer length Every published K quant and CD tier was scored on HumanEval+ (164) and MultiPL E 100 (llama.cpp, greedy T=0 ), with per problem completion length from token stats . The table replaces a bare file list — it shows, per tier, the actual code score, the exact size, the true bits per weight ( bpw = 8 × bytes ÷ 19,877,953,946 ), and whether the tier stays length tight or starts to ruminate at low bit. ⭐ marks a recommended pick . Tier Size bpw HE+ % HE+ tok p50/p90/max MPE 100 % MPE tok p50/p90/max : : : : Q8 0 21.16 GB 8.52 92.07 230/431/1002 88.33 85/188/1012 Q6 K L 17.98 GB 7.24 92.68 229/465/1748 89.67 84/179/603 Q6 K ⭐ 17.81 GB 7.17 92.07 238/442/3897 90.33 84/178/975 Q5 K L 15.25 GB 6.14 92.07 230/483/3374 89.00 84/193/1011 Q5 K M 15.07 GB 6.07 90.24 228/445/1715 89.67 85/184/981 Q4 K L 13.42 GB 5.40 92.07 251/457/…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy