Qwen3.8-27B on Apple M5 Max 128GB: not measured yet

Runs we already have

No run has been checked for this RAM case (M5 Max with 128GB unified memory) yet.

Other setups: these runs don't answer this RAM case (M5 Max with 128GB unified memory)

• Other setup, RAM case not checked: r_z6--z4sihzt · RTX 4090 (24GB) · 41.8 tok/s decode (chat-short) · measured by llm-speed (@llmspeed)
• Other setup, RAM case not checked: r_do9h933nvme · RTX 4090 (24GB) · 43.1 tok/s decode (chat-short) · measured by llm-speed (@llmspeed)
• Other setup, RAM case not checked: r_qfrb2zmyk0k · RTX 5090 (32GB) · 75.2 tok/s decode (chat-short) · measured by llm-speed (@llmspeed)
• Other setup, RAM case not checked: r_ptct8o01o5l · RTX 3090 (24GB) · 37.6 tok/s decode (chat-short) · community run
• Other setup, RAM case not checked: r_11kn1epxewh · RTX 4090 (24GB) · 43.1 tok/s decode (chat-short) · community run
• Other setup, RAM case not checked: r_dz5a3lzxhrj · RTX 5090 (32GB) · 65.7 tok/s decode (chat-short) · measured by llm-speed (@llmspeed)
• Other setup, RAM case not checked: r_c3ps9wjygi9 · RTX 5090 (32GB) · 65.7 tok/s decode (chat-short) · measured by llm-speed (@llmspeed)
• Other setup, RAM case not checked: r_7mod38qsldj · RTX 5090 (32GB) · 65.4 tok/s decode (chat-short) · measured by llm-speed (@llmspeed)

Run it yourself

Start llama-server with the model (flags below are a starting point; adjust offload to your machine), then point llm-speed at it. Add --llama-args='...' with the flags you used so the run records them.

pipx install llm-speed   # or: pipx upgrade llm-speed
# any recent llama.cpp release
llama-server -m /path/to/MODEL.gguf --port 8080 -ngl 999
# then, in a second terminal:
LLAMA_CPP_SERVER_URL=http://127.0.0.1:8080 \
  llm-speed bench --backend llama.cpp \
  --model /path/to/MODEL.gguf \
  --workload chat-short

The upload is signed and public. How contributing works · what the CLI sends.