Qwen3-Coder-30B-A3B-Instruct-4bit
6 workload results across 2 hardware configurations.
Fastest local config
259.9 decode tok/s
on RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB via llama.cpp. see full run
Local runs (6 runs)
Runs from contributors' own machines via MLX, llama.cpp, vLLM, exllamav2, or ollama. Signed on the submitter's hardware.
RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | llama.cpp | - | 68.41tok/s | no data | 334ms | r_pm_a1uf2ufc |
| chat-long | llama.cpp | - | 70.55tok/s | no data | 1,204ms | r_pm_a1uf2ufc |
| concurrent-decode | llama.cpp | - | 68.04tok/s | no data | no data | r_pm_a1uf2ufc |
| agent-trace | llama.cpp | - | 66.09tok/s | 4,816.7tok/s | 451ms | r_pm_a1uf2ufc |
| chat-short | llama.cpp | - | 259.9tok/s | no data | 218ms | r_c7qyvvmmsv1 |
M3 Ultra (60-core GPU) + 96GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | - | 112.2tok/s | 204.0tok/s | 539ms | r_fpsca03u2o_ |