Measurement wanted · request OPP-0103 · opened 2026-10-31
DeepSeek-V4.1-Flash on a 12GB GPU with 64GB system RAM: not measured yet
We don't have a DeepSeek-V4.1-Flash speed run on a 12GB GPU with 64GB system RAM 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.
What's being requested
- Model
- DeepSeek-V4.1-Flash · unsloth/DeepSeek-V4.1-Flash-1017-GGUF
- Hardware
- a 12GB GPU with 64GB system RAM (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)
- Suggested quant
- UD-IQ1_S, about 233 GB download
Memory guidance comes from the publisher, not from us: see Unsloth's guide.
Runs we already have
No DeepSeek-V4.1-Flash runs on any hardware yet.
Run it yourself
Stock llama.cpp loads this model from release b11870 on (PR #31086 merged upstream). Use b12018 or later. Release page.
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
# llama.cpp b12018 or later; N = the smallest value that fits your VRAM
llama-server -m /path/to/DeepSeek-V4.1-Flash-1017-UD-IQ1_S-00001-of-00005.gguf --port 8080 \
-ngl 999 --n-cpu-moe N -ot per_layer_token_embd.weight=CPU -lm mmap -lzm on -fa on
# then, in a second terminal:
LLAMA_CPP_SERVER_URL=http://127.0.0.1:8080 \
llm-speed bench --backend llama.cpp \
--model /path/to/DeepSeek-V4.1-Flash-1017-UD-IQ1_S-00001-of-00005.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.