FRONTIER BENCHMARKS
Benchmark reports
Every report is tested first-hand, dated, and reproducible from the published config. Filter to find the GPU, model, or backend decision you're working on.
FILTERS
3 OF 3 REPORTS
- BM-0032026-07-2738.6 tok/s · 740ms TTFT
Qwen3-Coder-30B-A3B quantization sweep: Q4_K_M vs. Q6_K vs. Q8_0 on Arc B60 Pro
On 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.
vulkanq6-kcodingintel-arc - BM-0022026-07-2652.1 tok/s · 410ms TTFT
Qwen3-Coder-30B-A3B: NVIDIA CUDA vs. Arc Vulkan at Q4_K_M
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. If your workload is latency-sensitive and CUDA is an option, NVIDIA still wins. Arc remains the better $/tok for budget builds.
cudaq4-k-mcodingnvidia - BM-0012026-07-2543.8 tok/s · 580ms TTFT
Qwen3-Coder-30B-A3B on Arc B60 Pro vs. dual RX 9700
Vulkan on Intel Battlemage lands within 12% of dual-RX 9700 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.
vulkanq4-k-mcodingintel-arc