Back to Quant Hub

Qwen2.5 1.5B Instruct

1.5B

Alibaba Qwen2.5

Tiny Qwen with 128K context. Surprisingly capable for summarisation and chat.

⬇ 283.6K HF downloads♥ 121 likesQwen/Qwen2.5-1.5B-Instruct-GGUF· stats from 6/24/2026
Consumer GPUMac / Apple SiliconCPU / VPS

131K

Max Context

2

Quant Variants

GGUF Q8_0

Best Quality

99.6%

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

FormatLevelBPWVRAMPPL LossSpeedActions
GGUFQ4_K_M4.851.4 GB4.0%480 tok/s
CalcHF
GGUFQ8_08.52.2 GB0.4%410 tok/s
CalcHF