Measurement wanted · request DR-002 · opened 2026-10-31
Qwen3.8-Flash-Next on Apple M5 Pro 48GB: not measured yet
We don't have a Qwen3.8-Flash-Next speed run on Apple M5 Pro 48GB yet, so there is no tokens-per-second number here. People asked for it, and this page is where the result will appear. Anyone with that hardware can run it with the free llm-speed CLI, and we'll post it as a community run.
We're also measuring this on an M5 Max 48GB.
What's being requested
- Model
- Qwen3.8-Flash-Next · unsloth/Qwen3.8-Flash-Next-GGUF
- Hardware
- Apple M5 Pro 48GB (the CLI records the machine's total RAM, rounded to 8 GB, not a container limit, so only runs checked for this RAM case count)
- Also requested
- Apple M5 Max 48GB, RTX 3090, RTX 4090, RTX 5090, RTX 3060 12GB
Runs we already have
No Qwen3.8-Flash-Next runs on any hardware yet.
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-shortThe upload is signed and public. How contributing works · what the CLI sends.
Get an alert
Email alerts for this page are switching on soon. Until then, follow @llmspeed on X, where new runs are posted.