Can the RTX 5090 D run deepseek-v4-flash-0731-spark?
No. deepseek-v4-flash-0731-spark needs about 36.8 GB at Q4_K_M (weights plus 1.8 GB runtime overhead), and the RTX 5090 D has 32 GB, so it won't fit without offloading layers to system RAM, which is far slower.
Every quantization
deepseek-v4-flash-0731-spark (60.3B) on 32 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 35 GB | 36.8 GB | Too big | - |
| Q5_K_M | 43 GB | 44.8 GB | Too big | - |
| Q8_0 | 65 GB | 66.8 GB | Too big | - |
| FP16 | 121 GB | 122.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 5090 D's 1790 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
What to do instead
Two ways forward
Cheapest cards that run it
- NVIDIA RTX A6000 - 48 GB, ~$3,299
- Mac Studio M4 Ultra - 192 GB, ~$4,699
- NVIDIA RTX 6000 Ada Generation - 48 GB, ~$5,800
- NVIDIA L40S - 48 GB, ~$8,500
Models that fit the RTX 5090 D
- Qwen3.6 35B A3B - 36B, 21 GB at Q4
- dolphin-2.9.1-yi-1.5-34b - 34.4B, 20 GB at Q4
- Laguna-XS-2.1 - 33.4B, 19 GB at Q4
- Gemma 4 31B - 32.7B, 19 GB at Q4
Compare
Same model, other hardware - and other models on this card
deepseek-v4-flash-0731-spark on other hardware
- RTX 6000D~26 tok/s
- MacBook Pro 16" M4 Max~8.9 tok/s
- DGX Spark (GB10)~4.5 tok/s
- RTX Spark N1X (128 GB)~4.5 tok/s
Also runs on the RTX 5090 D
- Qwen3.6 35B A3B~391 tok/s
- dolphin-2.9.1-yi-1.5-34b~51 tok/s
- Laguna-XS-2.1~54 tok/s
- Gemma 4 31B~54 tok/s
- OTel-2.0-LLM-31B-IT~54 tok/s
- Qwen3 32B~54 tok/s
- OTel-2.0-LLM-31B-IT-QLoRA~57 tok/s
- Qwen3.6 27B~64 tok/s
Frequently asked
Quick answers
Can the GeForce RTX 5090 D run deepseek-v4-flash-0731-spark?
No. deepseek-v4-flash-0731-spark needs about 36.8 GB at Q4_K_M (weights plus 1.8 GB runtime overhead), and the RTX 5090 D has 32 GB, so it won't fit without offloading layers to system RAM, which is far slower.
How much VRAM does deepseek-v4-flash-0731-spark need?
About 35 GB of weights at Q4_K_M, 65 GB at Q8_0 and 121 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is deepseek-v4-flash-0731-spark on the RTX 5090 D?
It doesn't fit in the RTX 5090 D's memory, so speed depends on how many layers you offload to system RAM - typically single-digit tokens per second or lower.