Q4_K_M · 4K context
DeepSeek-V4-Flash-0731 (MoE) MoE model with 304B total parameters and 13B active per token · estimated Q4_K_M memory about 181GB
Large MoE model with a total of 304B parameters (13B active) supporting 1,048,576 (1M) token contexts (max_position_embeddings). The official example uses 4×GB300 nodes, and the community compressed version must be checked separately for actual size and runtime compatibility for each artifact.
- Estimated Q4_K_M memory
- about 181GB
- total parameters
- 304B
- active parameter
- 13B
- native context
- 1024K
Start with a model
Find hardware for this model
Also running document search?
Reserve this for embedding and reranking models sharing the same GPU or unified memory. Leave it at none if they run separately on the CPU.
Matching devices 7· 5 shown
Comfortable fit · Q4_K_M · Headroom 55.5GB
₩19,250,000
112.5 ~ 125 tok/s
Comfortable fit · Q4_K_M · Headroom 51.5GB
₩19,818,800
25.6 ~ 41 tok/s
Comfortable fit · Q4_K_M · Headroom 299.5GB
₩25,000,000
76.8 ~ 85.3 tok/s
Comfortable fit · Q4_K_M · Headroom 299.5GB
₩38,475,000
112.5 ~ 125 tok/s
Can run · check speed · Q4_K_M · Headroom 0.0GB
₩14,600,000
4.9 ~ 4.9 tok/s
Price is the range midpoint, with a basic host added for GPU-only prices. Speed is an estimate for the same model and 4K input.
DeepSeek-V4-Flash-0731 (MoE) Local Serving Run Recipe
Selecting a device changes the quantization, safety context, GPU offload, Flash Attention, KV cache, and batch start values.
If you want to choose equipment again
You can first narrow down the model configurations based on budget, noise level, operating system and whether it's acceptable used.