DeepSeek-V4-Flash-0731-ROCmFP3

All projects

Apps & Tools

DeepSeek-V4-Flash-0731-ROCmFP3

Optimized DeepSeek-V4-Flash for 128GB AMD Strix Halo systems

bymrciffa

Playable

DeepSeek-V4-Flash-0731-ROCmFP3 media is blocked

Allow external media to connect to the provider and play this content.

Description

A mixed-precision ROCmFPX quantization of DeepSeek-V4-Flash-0731, specifically optimized for AMD Strix Halo hardware. It achieves an 82/92 evaluation score on standard benchmarks and runs unsplit on the Radeon 8060S iGPU, delivering up to 22.3 tokens per second in faster mode.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: Impressive optimization of a massive 284B parameter model to run locally on an integrated GPU with high performance.
Attributed to: mrciffa@davideciffa
Built with: V4.1 Flash Gemini 3.8 Flash Cyber 3.8 Flash Omni 1.1 Flash Ling 3.0 Flash Fin Gemini 3.7 Flash DeepSeek-V4-Flash-0731 Qwen3.7 Flash 3.6 Flash 3.5 Flash Cyber Step 3.7 Flash Gemini 3.5 Flash V4 2.5 Flash Redwood AI
Links: huggingface.co
View tweet
Tags: #quantization #rocm #gguf #strix-halo

Discovered: X
First posted: X · Sep 16, 2026
Listed: Added 2h ago
Build: Strong
Models: Strong