#intel-arc

A year ago Intel Arc was still a punchline for AI workloads. The Battlemage refresh (B580/B60) is the thing that changed that — and a year of driver, backend, and ecosystem work has made it genuinely good, with caveats. Here's where Arc actually stands for local AI in mid-2026.

We ran the same two 8B models on both cards with byte-identical weights and identical settings. The RX 7900 XT is ~3.9x faster — consistently across both architectures. Here's the full 2x2, what it actually tells you, and where we got the framing wrong the first time.

We benchmarked OpenVINO Model Server 2026.2.1 against llama.cpp Vulkan on the same Intel Arc Pro B60. OpenVINO is ~1.76x faster on a 30B-A3B model — and it works cleanly, contradicting our own earlier note that Battlemage was Vulkan-only. Here's the data and the correction.

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.

First cross-machine baseline of the lab. The same model — Qwen3.6-27B at Q4_K_M, identical Ollama digest a50eda8ed977 (byte-identical weights) — run on all four lab machines under controlled conditions (same 37-token prompt, 512 generated tokens, temperature 0, seed 42, one warmup rep). Result: the three CUDA/ROCm machines cluster within ~10% for generation (Ray 26.74, Evo-X2 25.21, Victor 24.28 tok/s), so for a 27B Q4_K_M model dual-12GB NVIDIA is NOT meaningfully faster than single-20GB AMD. The dual-GPU advantage only matters once the model exceeds ~18GB. Jitori's 8.41 tok/s is Vulkan-fallback performance, NOT the Arc B60's real capability (SYCL is broken on Battlemage — see bm-012). This directly answers Research Question RQ-001.

SUPERSEDED 2026-07-18 — see bm-009.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 Retained for history only; do not cite.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.'

Vulkan 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.

LFM2.5-8B-A1B (Q4_K_M, 8.47B total / ~1.7B active MoE params, 4.79 GiB) measured on TWO GPUs for a clean MoE-vs-GPU comparison: EvoX2's AMD Radeon RX 7900 XT (gfx1100, ROCm) at 269.01 tok/s gen / 7464.85 tok/s prompt using 6.81GB VRAM, and Jitori's Intel Arc Pro B60 (Battlemage, Vulkan) at 68.79 tok/s gen / 1688.53 tok/s prompt. The RX 7900 XT is ~3.9x faster on this MoE than the Arc B60 - the SAME ratio as on the dense Llama-3.1-8B (see bm-008), confirming the GPU gap is consistent across architectures. Companion to bm-011 (the APU iGPU result on the same machine). Closes the small-model and real-app workload gaps.

Llama-3.1-8B-Instruct (Q4_K_M, 8.03B dense params, 4.58 GiB) measured on TWO GPUs for a clean dense-vs-GPU comparison: Jitori's Intel Arc Pro B60 (Battlemage, Vulkan) at 27.01 tok/s gen / 706.61 tok/s prompt, and EvoX2's AMD Radeon RX 7900 XT (gfx1100, ROCm) at 105.22 tok/s gen / 3210.77 tok/s prompt. The RX 7900 XT is ~3.9x faster on this dense 8B than the Arc B60 - the SAME ratio as on the MoE LFM2.5-8B (see bm-007), confirming the GPU gap is consistent across architectures. Closes the general-work workload and dense-general model-class gaps; the 9th of 10.

Qwen3-30B-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.