Modelpublic

backpack-run/Qwen2.5-0.5B-Instruct-GGUF

sourceHugging Faceapache-2.0updated 19d agoView on Hugging Face

4likes1.3kdownloads

Model Card

Qwen2.5-0.5B-Instruct — Backpack GGUF

GGUF quantizations of Qwen/Qwen2.5-0.5B-Instruct, tested for llama.cpp-compatible text inference and packaged for Backpack.

Model

Property	Value
Original model	`Qwen/Qwen2.5-0.5B-Instruct`
Original publisher	Qwen
Upstream revision	`7ae557604adf67be50417f59c2c2f167def9a775`
Architecture	Qwen2ForCausalLM
Parameters	494,032,768
Context length	32,768
Input modalities	text
Output modalities	text
License	apache-2.0

Available packages

Quantization	Size	Approx. RAM	Recommended for
Q4KM	379.4 MiB	1.54 GB	Most users
Q5KM	400.6 MiB	1.57 GB	Higher quality
Q8_0	506.5 MiB	1.72 GB	Plenty of memory

Memory values are estimates, not guarantees. Runtime configuration and context length change actual use.

Backpack recommendation

Recommended: Q4_K_M. It usually offers a practical quality, size, and speed balance for local inference.

Run with llama.cpp

Using the llama.cpp revision recorded below:

bash

llama-cli --model Qwen2.5-0.5B-Instruct-Q4_K_M.gguf --conversation

Run with Backpack

These artifacts and backpack-model.yaml are prepared for the Backpack AI workspace.

Validation

Package	Integrity	Load	Inference	Tokenizer
Q4KM	passed	passed	passed	passed
Q5KM	passed	passed	passed	passed
Q8_0	passed	passed	passed	passed

—Packaged: 2026-08-25T20:09:53.257172+00:00
—llama.cpp revision: de699957b92f490efebad149665b0dccf127eaff
—SHA-256 checksums: see checksums.sha256

—Qwen2.5-0.5B-Instruct-Q4_K_M.gguf: f58616eebad692c29540d110551e0adb4d43c2456857dce7a74be369a3e035ba
—Qwen2.5-0.5B-Instruct-Q5_K_M.gguf: 2dfb3fc4a087c12ba0f05825a7501bc4fe8060f32762622b917cbe6bccbbb128
—Qwen2.5-0.5B-Instruct-Q8_0.gguf: 4c110cbf4f201deda239f2c2863e98b535f52f1040f5cf070ed2544ffed37fa2

Provenance

The source model was resolved to immutable revision 7ae557604adf67be50417f59c2c2f167def9a775. It was converted with llama.cpp's convert_hf_to_gguf.py and quantized with llama-quantize; the exact tested revision is recorded above and in backpack-model.yaml.

License and attribution

Upstream declares apache-2.0. Review the upstream model card and comply with all applicable terms.

Backpack does not claim ownership of the original model. These artifacts are packaged and quantized distributions of the upstream model.

Disclaimer

Quantization can alter output quality. Memory estimates vary with runtime configuration, context length, and hardware.