8-16 MI50s Minimax M3 @19 tps TG (peak)
Summary
Reports a peak throughput of 19 tokens per second for the Minimax M3 model running on 8-16 MI50 GPUs.
Similar Articles
MI50s Qwen 3.6 27B @52.8 tps TG @1569 tps PP (no MTP, no Quant)
Benchmark results for running Qwen 3.6 27B on AMD MI50 GPUs using a custom vllm fork, achieving 52.8 tokens/s TG and 1569 tokens/s PP without quantization or MTP, demonstrating usability for agentic tasks on 2018 hardware.
@0xSero: Minimax-M3 running on 4x RTX Pro 6000s - 800k context - 4x concurrency at 250k - 70-120 tok/s - 2000 tok/s prefill no c…
Minimax-M3 is demonstrated running on 4x RTX Pro 6000 GPUs with 800k context, achieving 70-120 tok/s inference and 2000 tok/s prefill at 4x concurrency using 376GB VRAM in mxfp4 format.
6x MI50's (96gb) vs 6 P40's (144gb) running MiniMax M2.7 REAP 139B Q3_K_L
A user shares benchmark results comparing 6x AMD MI50 (96GB) vs 6x NVIDIA P40 (144GB) running MiniMax M2.7 REAP 139B Q3_K_L model, showing P40 faster in prompt processing but MI50 faster in token generation.
16x AMD MI50 32GB: GLM-5.2 Q4 at 12.2 tok/s with llama.cpp RPC
Describes running the GLM-5.2 model with 4-bit quantization at 12.2 tokens per second on a cluster of 16 AMD MI50 GPUs using llama.cpp's RPC, achieving coherent long-form generation at 10.7k context.
80 tok/sec and 128K context on 12GB VRAM with Qwen3.6 35B A3B and llama.cpp MTP
A user shares a configuration for achieving over 80 tokens per second with Qwen3.6 35B A3B on a 12GB VRAM GPU using llama.cpp and Multi-Token Prediction (MTP). The post includes benchmark results and specific command-line parameters to optimize performance.