DeepSeek V4 Flash 0731 hardware requirements
What is DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is DeepSeek's official release of V4 Flash from July 2026, replacing the preview with substantially stronger agentic skills, according to its card. It is a mixture-of-experts model with about 284B total and about 14B activated parameters, a one-million-token context and an attached speculative decoding module. It answers directly in chat mode or reasons first in thinking mode, with low, high or max reasoning effort. The weights are MIT licensed.
About the model
- Parameters
- 284.33B total · 13.8B active (MoE)
- Attention
- Compressed attention (KV stored in blocks of several tokens)
- Max context
- 1,048,576 tokens
- Released
- 2026-07-31
- Model card
- DeepSeek V4 Flash 0731 on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q2_K | 117.35 GB | Heavy loss | llama.cpp team · ggml-org |
| MXFP4baseline | 154.99 GB | Near-lossless | llama.cpp team · ggml-org |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k | 256k |
|---|---|---|---|---|---|---|---|
| Q2_K | 117.4 | 117.4 | 117.6 | 117.8 | 118.3 | 119.4 | 121.5 |
| MXFP4 | 155.0 | 155.1 | 155.2 | 155.4 | 156.0 | 157.0 | 159.1 |
Which GPUs can run DeepSeek V4 Flash 0731?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Filter this list by budget, type and context in the calculator
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Ultra · 256 GB | Runs great | est. 52.5 tok/s36.7–68.2theoretical estimate ±30% | MXFP4 | 155.6 / 179.2 GB | Unified memory | up to 256k | — | — |
| Apple M3 Ultra · 256 GB | Runs great | est. 37.4 tok/s26.2–48.6theoretical estimate ±30% | MXFP4 | 155.6 / 179.2 GB | Unified memory | up to 256k | — | — |
| Apple M2 Ultra · 192 GB | Runs slowly | est. 36.7 tok/s25.7–47.7theoretical estimate ±30% | MXFP4 | 155.0 GB RAM | CPU only | up to 256k |
| — |
| Apple M5 Max (40-core GPU) · 128 GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 42.7 tok/s29.9–55.5theoretical estimate ±30% | Q2_K | 117.4 GB RAM | CPU only | up to 256k |
| — |
| Apple M4 Max (40-core GPU) · 128 GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 38.4 tok/s26.9–49.9theoretical estimate ±30% | Q2_K | 117.4 GB RAM | CPU only | up to 256k |
| — |
| Ryzen AI Max+ 395 (Strix Halo) · 128 GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 19.1 tok/s13.4–24.9theoretical estimate ±30% | Q2_K | 117.4 GB RAM | CPU only | up to 256k |
| $1,999 launch MSRP (128 GB) |
| Apple M4 · 32 GB | Won't run | — | MXFP4 | needs 155.6 GB | — | — |
| — |
| Apple M4 Max (32-core GPU) · 36 GB | Won't run | — | MXFP4 | needs 155.6 GB | — | — |
| — |
| Apple M4 Pro · 64 GB | Won't run | — | MXFP4 | needs 155.6 GB | — | — |
| — |
| Apple M5 · 32 GB | Won't run | — | MXFP4 | needs 155.6 GB | — | — |
| — |
| Apple M5 Max (32-core GPU) · 36 GB | Won't run | — | MXFP4 | needs 155.6 GB | — | — |
| — |
| Apple M5 Pro · 64 GB | Won't run | — | MXFP4 | needs 155.6 GB | — | — |
| — |
| Apple M6 · 32 GB | Won't run | — | MXFP4 | needs 155.6 GB | — | — |
| — |
| Intel Arc B580 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $290 street (as of 2026-08-09) |
| DDR4-3200 dual-channel CPU · 64 GB | Won't run | — | MXFP4 | needs 155.0 GB | — | — |
| — |
| DDR5-5600 dual-channel CPU · 96 GB | Won't run | — | MXFP4 | needs 155.0 GB | — | — |
| — |
| DDR5-6000 dual-channel CPU · 96 GB | Won't run | — | MXFP4 | needs 155.0 GB | — | — |
| — |
| GeForce GTX 1080 Ti | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $699 launch MSRP |
| NVIDIA DGX Spark · 128 GB | Won't run | — | MXFP4 | needs 155.6 GB | — | — |
| $3,999 launch MSRP (128 GB) |
| GeForce RTX 2080 Ti | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 3050 8GB | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $249 launch MSRP |
| GeForce RTX 3060 12GB | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $250 street (as of 2026-08-09) |
| GeForce RTX 3070 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 3080 10GB | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 3080 12GB | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 3090 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $1,050 street (as of 2026-08-09) |
| GeForce RTX 3090 Ti | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $1,999 launch MSRP |
| GeForce RTX 4060 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $299 launch MSRP |
| GeForce RTX 4060 Laptop | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| — |
| GeForce RTX 4060 Ti 16GB | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $399 launch MSRP |
| GeForce RTX 4070 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Laptop | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| — |
| GeForce RTX 4070 Super | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Ti Super | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 4080 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $1,199 launch MSRP |
| GeForce RTX 4080 Laptop | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| — |
| GeForce RTX 4080 Super | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 4090 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $2,755 street (as of 2026-08-09) |
| GeForce RTX 4090 Laptop | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| — |
| GeForce RTX 5060 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $429 street (as of 2026-08-09) |
| GeForce RTX 5070 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $949 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| — |
| GeForce RTX 5080 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $1,256 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| — |
| GeForce RTX 5090 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $4,200 street (as of 2026-08-09) |
| GeForce RTX 5090 Laptop | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| — |
| Radeon RX 7800 XT | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $499 launch MSRP |
| Radeon RX 7900 XT | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $899 launch MSRP |
| Radeon RX 7900 XTX | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $999 launch MSRP |
| Radeon RX 9060 XT 16GB | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $449 street (as of 2026-08-09) |
| Radeon RX 9070 | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Won't run | — | MXFP4 | needs 155.1 GB | — | — |
| $689 street (as of 2026-08-09) |
Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.
Cheapest GPUs that run it
No GPU with a current street price reaches Runs great or Runs well at MXFP4. The table above lists Macs, unified-memory PCs and CPU setups.
Measured results for DeepSeek V4 Flash 0731
No public measurements for this model yet.
Frequently asked questions
How much VRAM does DeepSeek V4 Flash 0731 need?
At MXFP4 the file is 154.99 GB; with 8k context a graphics card needs about 155.1 GB (weights 154.42 GB, KV cache 0.1 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 117.4 GB. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.
What is the cheapest GPU that runs DeepSeek V4 Flash 0731 well?
No GPU with a current street price reaches Runs great or Runs well at MXFP4. The best tracked option is Apple M5 Ultra · 256 GB: Runs great.
Can DeepSeek V4 Flash 0731 run on an 8 GB, 16 GB or 24 GB GPU?
At MXFP4 with 8k context: GeForce RTX 4060 — Won't run; GeForce RTX 5060 Ti 16GB — Won't run; GeForce RTX 3090 — Won't run.
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.