DeepSeek V3.1

1 report

DeepSeek V3.1 VRAM requirements by size and quant →

How does DeepSeek V3.1 run on your hardware?

Pick your GPU or Mac, then read the speeds people reported for DeepSeek V3.1 on it, or estimate memory fit and speed.

Buying hardware? Compare GPUs →

Free to use. No account needed. Memory estimates and community measurements are labelled separately.

Run DeepSeek V3.1 yourself? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Benchmark with your agent Paste a result

Reported performance for DeepSeek V3.1

Filter this model’s reports by setup →

Thin page (1 of 3 reports needed for indexing). Add yours.

DeepSeek V3.1 671B Terminus

M5 Max 128GB · llama.cpp

generation:: 3.6 tokens/s
quant:: INT4 (GGUF)

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.

User reports running DeepSeek v3.1 671B Terminus at 3.6 tokens/sec on a MacBook Pro with M5 Max 128GB and 8TB storage. Setup uses a heavily modified slipstream llama.cpp base that caches MoE experts to disk and calls them in as they change, with a -0.1 bias in the MTP router for in-RAM experts. A custom GGUF-derived format uses BF16 for fixed layers and INT4 for expert layers. The user says it is working extremely well and generating a somewhat usable 3.6 tokens/sec.

Get a weekly email of new DeepSeek V3.1 reports on any GPU.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardware	Quant / engine	Reported context	Generation
DeepSeek V3.1 671B Terminus M5 Max 128GB	INT4 llama.cpp	Not reported	3.6 tokens/s