DeepSeek-R1-Distill-Qwen-7B

Deepseek-R1 family · 8.0B params

Evidence: 1 sourced run · 1 awaiting review · 1 independent source · first recorded May 10, 2026 · last recorded Aug 17, 2026. What these labels mean.

What the DeepSeek-R1-Distill-Qwen-7B numbers mean

The fastest verified result on our board is 39.8 output tok/s on an AMD RX 9060 XT 16GB at Q8_0 with a 4096-token context. That is about 25.2 ms per generated token — 500 tokens takes roughly 12.6 seconds. Prompt processing on the same record runs at 1844.1 tok/s, so a 2,000-token prompt is read in about 1.1 seconds. Peak VRAM was measured at 7.6 GB. Across the 2 records we hold for this model the range is 39.8–213.3 tok/s on 2 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does DeepSeek-R1-Distill-Qwen-7B need?

DeepSeek-R1-Distill-Qwen-7B has 8.0B 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-R1-Distill-Qwen-7B's parameter count. Full benchmark board.

All benchmarks Methodology