TAG
#30b-class
5 items — 0 dispatches5 benchmark reports.
Benchmark reports
BM-003Qwen3-Coder-30B-A3B quantization sweep: Q4_K_M vs. Q6_K vs. Q8_0 on Arc B60 Pro
2026-07-27On 24GB Arc, Q6_K is the sweet spot: quality recovers to within 2 points of Q8_0 on HumanEval while staying 38% faster and fitting comfortably. Q8_0 barely fits and leaves no room for context. Q4_K_M is the budget pick when VRAM is tight.
BM-002Qwen3-Coder-30B-A3B: NVIDIA CUDA vs. Arc Vulkan at Q4_K_M
2026-07-18SUPERSEDED 2026-07-18 — see bm-009. Provisional Victor numbers in this record were ~3x too slow (real: 172 tok/s gen, 3403 tok/s prompt) and based on an incorrect single-24GB-GPU hardware spec. Retained for history only; do not cite. The original summary read: 'CUDA on the NVIDIA reference produces 52.1 tok/s vs. 38.6 tok/s on Arc Vulkan — a 35% generation-speed lead at the same 24GB VRAM tier.'
BM-001Qwen3-Coder-30B-A3B on Arc B60 Pro vs. dual Radeon AI PRO R9700
2026-07-18Vulkan on Intel Battlemage lands within 12% of dual-Radeon AI PRO R9700 for code generation at Q4_K_M, at roughly half the system cost. Arc is the price-performance leader for sub-$2K builds; multi-GPU AMD wins raw throughput once you accept the complexity.
BM-009Qwen3-Coder-30B-A3B on Victor (RTX 5070 dual-GPU, CUDA) — bm-002 re-measurement
2026-07-18Re-measurement of the NVIDIA CUDA path that bm-002 reported provisionally. On Victor's dual RTX 5070 mobile config (Blackwell sm_120, CUDA 13.3), Qwen3-Coder-30B-A3B at Q4_K_M generates at 172 tok/s and processes prompts at 3403 tok/s — roughly 3.3x and 5.6x faster than bm-002's provisional figures (52.1 / 612.4). bm-002 is superseded; these are the real numbers.
BM-012Qwen3-30B-A3B INT4 on Arc B60: OpenVINO/OVMS vs llama.cpp Vulkan — backend shootout
2026-07-18Qwen3-30B-A3B-Instruct-2507 (INT4, OpenVINO IR) served via OpenVINO Model Server 2026.2.1 on Jitori's Intel Arc Pro B60 (Battlemage BMG G21, 24GB). Generates at 67.95 tok/s via the OpenAI streaming API - roughly 1.76x faster than the same B60 running Qwen3-Coder-30B-A3B Q4_K_M via llama.cpp Vulkan (bm-001, 38.6 tok/s). This is the backend comparison the dataset was missing: same GPU, same 30B-A3B model class, two Intel-GPU backends. Finding: OpenVINO is meaningfully faster than Vulkan on Battlemage for this workload. This also corrects a fleet assumption - OpenVINO's GPU plugin (Level Zero) works cleanly on this B60, contradicting the older 'SYCL is broken on Battlemage, Vulkan-only' note.