deepseek-v4-flash-0731-spark
> [!IMPORTANT] > Generation is validated on one physical NVIDIA DGX Spark. Use the pinned > Docker recipe below. Stock vLLM, stock ExLlamaV3, and a bare > --tensor-parallel-size 1 command cannot load this TP4 rank-sliced artifact > correctly.
Params
60.3 B
Context
1,048,576
Downloads 30d
171 K
Likes
51
Download history
tracking started — chart appears after 7 days of snapshots (1 recorded)171 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | i16 | 106.8 GB | 127.0 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 1024K ctx | 106.8 GB | 1,276.0 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/deepseek-v4-flash-0731-spark
{
"hf_id": "0xSero/deepseek-v4-flash-0731-spark",
"params_b": 60.31,
"context_length": 1048576,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 171151,
"vram_estimates": [
{ "quant": "i16", "gb": 127.0 }
],
"updated_at": "2026-10-25T01:00:24Z"
}
Specifications
- Architecture
- DeepseekV4ForCausalLM
- Parameters
- 60.3 B
- Tensor type
- I16
- Context length
- 1,048,576
- Vocabulary
- 129,280
- Layers / heads
- 43 / 64
- Licence
- mit
- First seen on the Hub
- 2026-08-01
- Base model
- DeepSeek-V4-Flash-0731
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-25
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model