DeepSeek-V4
DeepSeek-V4-Flash-0731
DeepSeek · open-permissive mit
| Parameters (B) | 304.18 |
|---|---|
| Architecture | moe |
| Layers / KV heads / head dim | 43 / 1 / 512 |
| Context window | 1048576 |
| Modalities | in: text; out: text |
| GGUF | available |
| Commercial use | yes |
Minimum hardware (estimate)
At Q4_K_M and 8k context, total working set ≈ 186.0 GiB. On a machine with 64 GiB system RAM and no discrete GPU: Won't run. Limiting factor: No GPU and system RAM insufficient for weights + KV.
Scores
| Benchmark | Value | Uncertainty | Run by | Source |
|---|---|---|---|---|
| GPQA Diamond | 91.0% | unknown | third-party | epoch-ai |
| OTIS Mock AIME 2024-2025 | 94.4% | unknown | third-party | epoch-ai |
| SimpleQA Verified | 34.7% | unknown | third-party | epoch-ai |
Provenance
- identity, license, architecture, parameter count: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731 (retrieved 2026-08-10)
HF: deepseek-ai/DeepSeek-V4-Flash-0731 · snapshot 2026-08-10