BM-001 · TESTED 2026-07-25

Qwen3-Coder-30B-A3B on Arc B60 Pro vs. dual Radeon AI PRO R9700

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.

vulkan · q4-k-m · llama.cpp b3500

Configuration

Artifact: Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf
Author: Edgar
Backend: vulkan
Checksum: sha256:pending-real-checksum
Context length: 8192 tokens
Model: Qwen3-Coder-30B-A3B-Instruct
Quantization: q4-k-m
Runtime: llama.cpp b3500
Settings: -ngl 99 -c 8192 -t 8 -b 512 --no-mmap
Workload pack: workload-pack-v1

Results

100-prompt HumanEval-style coding suite plus 20-prompt long-context refactor task. 3 warmup runs, 5 measured runs averaged, variance reported.

MACHINE	PROMPT tok/s	GEN tok/s	TTFT ms	VRAM GB	RAM GB	POWER W
Jitori PC Single Arc B60 Pro, Vulkan (ANV 25.2.8). GGML_VK_VISIBLE_DEVICES=1.	412.3	38.6	740	18.1	3.2	245
Ray Dual Radeon AI PRO R9700 (gfx1201, RDNA4), Vulkan. Single-GPU results; second card idles for this workload size.	538.9	43.8	580	17.9	3.1	410

Quality scores

coding

0.81 / 0-1

HumanEval pass@1

Limitations

Q4_K_M trades measurable quality for memory; pair with the Q6_K comparison (bm-003) before final decisions.
Single-GPU Ray result underuses the second Radeon AI PRO R9700; combined-GPU scaling is a separate benchmark.
Vulkan-only for Arc per Battlemage SYCL instability; CUDA path on Victor is reported separately (bm-002).

Corrections

2026-07-18: Ray GPU identity corrected from 'RX 9700 (RDNA3)' to 'Radeon AI PRO R9700 (gfx1201, RDNA4)'. Measurement values unchanged — this is a labeling correction only. [D-007]

RAW DATA → How we test →

RELATED EQUIPMENT GUIDES

If these numbers point you toward hardware, these buyer-intent guides go deeper. Links below are editorial; they carry no affiliate tag.

The measured GPU buyer's guide
Turn this result into a hardware decision.
How much VRAM you actually need
Will your target model fit?
Build a rig around these numbers
A complete sub-$1,000 local-AI lab.