BM-002TESTED 2026-07-26
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-mllama.cpp b3500 (CUDA 12.5)codingnvidiaintel-arccudavulkan30b-class
Configuration
- Model
- Qwen3-Coder-30B-A3B-Instruct
- Artifact
- Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf
- Checksum
- sha256:pending-real-checksum
- Quantization
- q4-k-m
- Context length
- 8,192 tokens
- Backend
- cuda
- Runtime
- llama.cpp b3500 (CUDA 12.5)
- Settings
- -ngl 99 -c 8192 -t 8 -b 512
- Workload pack
- workload-pack-v1
- Author
- Edgar
- Reviewer
- Edgar
Results
Same workload pack as bm-001 to enable direct comparison.
52.1tok/s
GEN · Victor
612tok/s
PROMPT
410ms
TTFT
18.0GB
VRAM USED
| MACHINE | PROMPT tok/s | GEN tok/s | TTFT ms | VRAM GB | RAM GB | POWER W |
|---|---|---|---|---|---|---|
Victor NVIDIA CUDA reference. cuBLAS, standard memory pool. | 612.4 | 52.1 | 410 | 18.0 | 2.8 | 285 |
Jitori PC Arc B60 Pro, Vulkan. Reference from bm-001. | 412.3 | 38.6 | 740 | 18.1 | 3.2 | 245 |
Quality scores
CODING
0.81/ 0-1
HumanEval pass@1
Limitations
- ◆Victor configuration is provisional pending identity confirmation (see blueprint Appendix A1).
- ◆CUDA version pinned to 12.5; cuBLAS behavior varies across minor versions.
- ◆Identical model artifact and quant to bm-001 to isolate the backend variable.