AI가 움직이고 미래가 업데이트됩니다.Ling-3.0-flash-VL-MTP-ROCmFP4-GGUF
`inclusionAI/Ling-3.0-flash-VL` (124B total / 5.5B active, native multimodal) quantized to ROCmFP4 for AMD Strix Halo, **with a multi-token-prediction head grafted in** from its text sibling — and with the server fix that lets **MTP and images work at the same time**, which they do not in stock llama.cpp. Everything below was measured on the shipped files on one Ryzen AI Max+ 395 (Radeon 8060S, 128 GiB unified). Numbers come from the built GGUFs and from server logs, never from estimates. ⚠️ **COHERENT is the worst of the three on this model** even though it is the largest and the highest bit-width (4.70 bpw vs 4.38). Its PPL is 0.80 worse than STRIX_LEAN — roughly 3.5σ against the ±0.23 error bars — and it is slower on both prefill and decode. It ships for completeness; it is not the "quality" option here. Tier ranking is model-dependent and has to be measured, not assumed.
번역 준비 중입니다. 원문을 표시합니다.
`inclusionAI/Ling-3.0-flash-VL` (124B total / 5.5B active, native multimodal) quantized to ROCmFP4 for AMD Strix Halo, **with a multi-token-prediction head grafted in** from its text sibling — and with the server fix that lets **MTP and images work at the same time**, which they do not in stock llama.cpp. Everything below was measured on the shipped files on one Ryzen AI Max+ 395 (Radeon 8060S, 128 GiB unified). Numbers come from the built GGUFs and from server logs, never from estimates. ⚠️ **COHERENT is the worst of the three on this model** even though it is the largest and the highest bit-width (4.70 bpw vs 4.38). Its PPL is 0.80 worse than STRIX_LEAN — roughly 3.5σ against the ±0.23 error bars — and it is slower on both prefill and decode. It ships for completeness; it is not the "quality" option here. Tier ranking is model-dependent and has to be measured, not assumed.