DeepSeek
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is an open-weights 162B-parameter model by DeepSeek. It holds an Intelligence score of 77.5 on the local.ai leaderboard (2026-08 snapshot).
open weights
77.5
local.ai Intelligence
Parameters
162B
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2026-08-01
Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.
Does it fit your hardware?
Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.
Q4_K_M 94GQ6_K 145.8GQ8_0 178.2GFP16 324G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 43.7 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 58.3 GB | Very small |
| Q3_K_M | 74.5 GB | Small |
| NVFP4 | 81 GB | NVIDIA 4-bit |
| Q4_K_S | 87.5 GB | Common |
| Q4_K_M | 94 GB | Most common sweet spot |
| Q5_K_M | 123.1 GB | Balanced |
| Q6_K | 145.8 GB | Near-lossless |
| Q8_0 | 178.2 GB | Near-lossless |
| FP16 | 324 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| model-00048-of-00048.safetensors | 3.44 GB |
| model-00046-of-00048.safetensors | 3.36 GB |
| model-00004-of-00048.safetensors | 3.35 GB |
| model-00012-of-00048.safetensors | 3.34 GB |
| model-00014-of-00048.safetensors | 3.34 GB |
| model-00016-of-00048.safetensors | 3.34 GB |
GGUF: unsloth/DeepSeek-V4-Flash-0731-GGUF · 306,443 downloads
| File | Size | |
|---|---|---|
| UD-IQ1_M/DeepSeek-V4-Flash-0731-UD-IQ1_M-00001-of-00003.gguf | 0.00 GB | download |
| UD-IQ1_M/DeepSeek-V4-Flash-0731-UD-IQ1_M-00002-of-00003.gguf | 46.05 GB | download |
| UD-IQ1_M/DeepSeek-V4-Flash-0731-UD-IQ1_M-00003-of-00003.gguf | 34.88 GB | download |
| UD-IQ1_S/DeepSeek-V4-Flash-0731-UD-IQ1_S-00001-of-00003.gguf | 0.00 GB | download |
| UD-IQ1_S/DeepSeek-V4-Flash-0731-UD-IQ1_S-00002-of-00003.gguf | 45.72 GB | download |
| UD-IQ1_S/DeepSeek-V4-Flash-0731-UD-IQ1_S-00003-of-00003.gguf | 31.14 GB | download |
| UD-IQ2_M/DeepSeek-V4-Flash-0731-UD-IQ2_M-00001-of-00003.gguf | 0.00 GB | download |
| UD-IQ2_M/DeepSeek-V4-Flash-0731-UD-IQ2_M-00002-of-00003.gguf | 46.53 GB | download |
| UD-IQ2_M/DeepSeek-V4-Flash-0731-UD-IQ2_M-00003-of-00003.gguf | 38.15 GB | download |
| UD-IQ2_XXS/DeepSeek-V4-Flash-0731-UD-IQ2_XXS-00001-of-00003.gguf | 0.00 GB | download |
| UD-IQ2_XXS/DeepSeek-V4-Flash-0731-UD-IQ2_XXS-00002-of-00003.gguf | 46.46 GB | download |
| UD-IQ2_XXS/DeepSeek-V4-Flash-0731-UD-IQ2_XXS-00003-of-00003.gguf | 38.15 GB | download |
GGUF: huihui-ai/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF · 243,479 downloads
| File | Size | |
|---|---|---|
| DeepSeek-V4-Flash-Q2-0731.gguf | 80.76 GB | download |
| DeepSeek-V4-Flash-Q2_K-0731.gguf | 90.89 GB | download |
| DeepSeek-V4-Flash-Q4-mxfp4-0731.gguf | 145.26 GB | download |
| DeepSeek-V4-Flash-Q4_K-0731.gguf | 153.33 GB | download |
| dspark-abliterated/dspark-DeepSeek-V4-Flash-0731-BF16.gguf | 10.54 GB | download |
| dspark-abliterated/dspark-DeepSeek-V4-Flash-0731-Q8_0.gguf | 10.15 GB | download |
| dspark/dspark-DeepSeek-V4-Flash-0731-BF16.gguf | 10.54 GB | download |
| dspark/dspark-DeepSeek-V4-Flash-0731-Q8_0.gguf | 10.15 GB | download |
What you save self-hosting this model
Uses the model's own API price when it exists; otherwise the closest commercial equivalent.
Waiting for hardware detection…
Related models
RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.