Measurement wanted · request DR-028 · opened 2026-11-19
Hy4 Flash on 4× RTX 3090: not measured yet
We don't have a Hy4 Flash speed run on 4× RTX 3090 yet, so there is no tokens-per-second number here. People asked for it, and this page is where the result will appear.
We haven't measured its speed yet. Four 24GB cards total 96 GiB of VRAM, which is less than 125.73 GiB, so the full published file does not fit in that VRAM. Offload is untested by us. Not in stock llama.cpp, Ollama or LM Studio yet. llama.cpp#32517 (https://github.com/ggml-org/llama.cpp/pull/32517) is open and still a draft (checked 19 November 2026). Check back. File-size fit only: https://llm-speed.com/m/hy4-flash
What's being requested
- Model
- Hy4 Flash · AngelSlim/Hy4-flash-GGUF
- Hardware
- 4× RTX 3090
- Also requested
- Apple M5 Max 128GB, 128GB Spark
Runs we already have
No Hy4 Flash runs on any hardware yet.
Get an alert
Email alerts for this page are switching on soon. Until then, follow @llmspeed on X, where new runs are posted.