Qwen3-1.7B-Base Q4_K_M

Mobile CPUvivo X300SME2

This is a 4-bit weight-quantized version of Qwen/Qwen3-1.7B-Base packaged as a single GGUF file for edge deployment on ARM CPUs using llama.cpp. The model was quantized with llama.cpp's native Q4_K_M k-quant recipe, guided by an importance matrix (llama-imatrix) computed over a plain-text calibration corpus, and it runs on device through ggml CPU_REPACK kernels compiled with -march=armv8.6-a+dotprod+i8mm. Quantization is weight-only — activations stay float at runtime, so there is no activation calibration and no runtime quantization step to configure. The tokenizer, merges, special tokens and chat template are embedded in the GGUF, so a single file is all you need to run the model.View on Hugging Face

Accuracyvs base model

MMLU (0-shot)61.05%↓0.18 pp

Tokens / sec

34.11

About this version

Original Model:: Qwen3-1.7B-Base by Alibaba Cloud — Repository
Optimization/conversion:: Arm-Optimized version for execution on Arm-based platforms.
Converted/optimized by:: Arm
License:: The Original Model and the Optimized Model are subject to Apache-2.0.

This repository contains a converted or optimized version of the Original Model (the “Optimized Model”). The Original Model has been converted or optimized as described above for execution on Arm-based platforms.

No retraining or fine-tuning of the Original Model was performed as part of the conversion or optimization. The conversion or optimization was not intended to change the Original Model’s behavior or intended use.

Original Model and Documentation

For information about the Original Model, including its development, training data, intended uses, limitations and other relevant information, please refer to the Original Model repository. Information in that repository was provided by the original developer or other third parties and, unless expressly stated otherwise, has not been independently verified by Arm.

Licenses and Third-Party Terms

Use of the Original Model and the Optimized Model is subject to the applicable licenses, usage restrictions and other terms identified above and in the relevant repositories. Publication of the Optimized Model does not grant any rights beyond those provided under the applicable license terms.

You are responsible for reviewing those terms and ensuring that your use of the Original Model and the Optimized Model is permitted.

About this version

Original Model:: Qwen3-1.7B-Base by Alibaba Cloud — Repository
Optimization/conversion:: Arm-Optimized version for execution on Arm-based platforms.
Converted/optimized by:: Arm
License:: The Original Model and the Optimized Model are subject to Apache-2.0.

Original Model and Documentation

Licenses and Third-Party Terms

You are responsible for reviewing those terms and ensuring that your use of the Original Model and the Optimized Model is permitted.

Metric	Resultsvs baseline	Change
End to end latency p50	4564.02ms80551.18ms	−75987.16 ms
Peak memory	2311.20MB3377.73MB	−1066.52 MB
Tokens per second	34.11tok/s2.77tok/s	+31.34 tok/s
Time to first token	809.13ms34330.38ms	−33521.25 ms
MMLU (0-shot)	61.05%61.23%	−0.18%

Configuration	Baseline	Arm Optimized
Dataset	MMLU (test)	MMLU (test)
Sample count	14,042	14,042
Batch size	1	1
Prompt length	128	128
Generation length	128	128
Runs	20	20
Warmup runs	5	5

Qwen3-1.7B-Base Q4_K_M

Qwen3-1.7B-Base Q4_K_M

Get Started with this Model

Topo llama.cpp WebUI Chat

Model Evaluation

Configuration

Purpose of this Release

Comparability