DeepSeek V4 Flash (MXFP4)
antirez's MXFP4 community GGUF of DeepSeek V4 Flash 0731 — the July 2026 re-post-trained 284B-parameter Mixture-of-Experts (~13B active per token) with 1M-token context and Compressed Sparse Attention. Routed experts use the MXFP4 micro-scaled 4-bit block format while attention projections, shared experts, router, embeddings, and output head stay at Q8_0 / F16, landing at ~156 GB — close to the native FP4 build's footprint and the highest-fidelity single-file ds4 variant. Needs a workstation or Mac Studio-class machine with ~200 GB of usable memory. Produced for antirez's ds4 inference engine.
| At a glance | |
|---|---|
| Made by | DeepSeek |
| Download size | 156.0 GB |
| Parameters | 284B |
| Quantization | MXFP4 |
| Context window | 1000K tokens |
| Uses tools | Yes |
| Best for | Reasoning |
| Runs on | llama.cpp, DwarfStar |
| License | MIT |
| Added to the catalog | 2026-08-01 |
Gezel downloads this model the first time a gezel needs it, checks the file against its published hash, and applies tuned settings for it.