The experimental vision variant of DeepSeek-V4-Flash: image-text input, MIT licensed, FP8 weights.
0
Quantized builds
1
Benchmark records
Quantized builds
Community and official quantized releases; "linked records" counts only benchmarks tied to that exact release.
No quantized builds cataloged yet.
Benchmark data
1 configurations
| Hardware | Framework | Quant | Decode | VRAM used | Samples | Evidence |
|---|---|---|---|---|---|---|
| 2x NVIDIA RTX 5090 | llama.cpp | UD-Q8_K_XL | 32.1 tok/s | 60.59 GB | 1 | L0 Self-reported |
1 of these records are not linked to a specific quantized build; the full set is on the search page.
Community discussion
No discussions yet — start the first one.
Start a discussion