DeepSeek-V4-Pro-Qwen3.5-9B-MTP

Deepseek family · 9.0B params

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Aug 9, 2026. What these labels mean.

What the DeepSeek-V4-Pro-Qwen3.5-9B-MTP numbers mean

The fastest result on our board is 43.4 output tok/s on an RTX 3090 at Q8_0 with a 2048-token context. That is about 23.0 ms per generated token — 500 tokens takes roughly 11.5 seconds. Prompt processing on the same record runs at 107.1 tok/s, so a 2,000-token prompt is read in about 18.7 seconds.

How much VRAM does DeepSeek-V4-Pro-Qwen3.5-9B-MTP need?

DeepSeek-V4-Pro-Qwen3.5-9B-MTP has 9.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Models with a similar footprint

Ranked by distance from DeepSeek-V4-Pro-Qwen3.5-9B-MTP's parameter count. Full benchmark board.

All benchmarks Methodology