keys-DeepSeekV4Flash-Vision-EXP-ablit

Deepseek family · 305.0B params

Evidence: 1 sourced run · 1 independent source · first recorded Sep 1, 2026. What these labels mean.

What the keys-DeepSeekV4Flash-Vision-EXP-ablit numbers mean

The fastest verified result on our board is 66.8 output tok/s on an RTX 3090 x8 at FP8 with a 131072-token context. That is about 15.0 ms per generated token — 500 tokens takes roughly 7.5 seconds. Prompt processing on the same record runs at 1088.3 tok/s, so a 2,000-token prompt is read in about 1.8 seconds. Peak VRAM was measured at 183.1 GB.

How much VRAM does keys-DeepSeekV4Flash-Vision-EXP-ablit need?

keys-DeepSeekV4Flash-Vision-EXP-ablit has 305.0B 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 keys-DeepSeekV4Flash-Vision-EXP-ablit's parameter count. Full benchmark board.

All benchmarks Methodology