Qwen3.8-4B-Distill

Qwen family · 4.0B params

1recorded run

97.1best tok/s

1verified

Evidence: 1 sourced run · 1 independent source · first recorded Sep 2, 2026. What these labels mean.

What the Qwen3.8-4B-Distill numbers mean

The fastest verified result on our board is 97.1 output tok/s on an RTX 2060 Super at Q4_K_M with a 8192-token context. That is about 10.3 ms per generated token — 500 tokens takes roughly 5.1 seconds. Prompt processing on the same record runs at 2145.7 tok/s, so a 2,000-token prompt is read in about 0.9 seconds. Peak VRAM was measured at 3.0 GB.

How much VRAM does Qwen3.8-4B-Distill need?

Qwen3.8-4B-Distill has 4.0B 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.

Quantisation	Estimated VRAM	Smallest card that fits
Q4_K_M (4-bit)	3.4 GB	8 GB
Q8_0 (8-bit)	5.7 GB	8 GB
FP16 (16-bit)	10.0 GB	12 GB

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.

Fastest GPUs for this model (best tok/s)

RTX 2060 Super97.1

Models with a similar footprint

Model	Params	Q4_K_M weights
gemma-3n-E4B-it-text	4B	2.2 GB
NVIDIA-Nemotron-3-Nano-4B	4B	2.2 GB
Phi-4-mini-reasoning	4B	2.2 GB
Qwen3-4B	4B	2.2 GB
Qwen3-4B-Thinking-2507	4B	2.2 GB
Qwen3.5-4B	4B	2.2 GB

Ranked by distance from Qwen3.8-4B-Distill's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX 2060 Super · 8 GB	Qwen3.8-4B-Distill	Q4_K_M	llama.cpp b10449 (0d9ceae1e38291035605613ab41a…	8192	97.1 ✓	2145.7	3.0	src