---
language:
- en
library_name: llama.cpp
pipeline_tag: text-generation
tags:
- gguf
- qwen3
- quantized
- on-device
- lumen
base_model:
- Qwen/Qwen3-1.7B
---

# Lumen Qwen3 1.7B shared-base GGUF

This card documents the single shared-base artifact
`lumen-qwen3-fast-shared-q4_k_m.gguf` in
`ales27pm/lumen-qwen3-bootstrap-gguf`. Lumen uses it as the common base for
role-specific LoRA adapters in its local-first iOS runtime.

## Immutable artifact identity

| Field | Value |
| --- | --- |
| Lumen repository | `ales27pm/lumen-qwen3-bootstrap-gguf` |
| Lumen repository revision | `8abae6d695408dbc75a134212dd616cd14549ae1` |
| Lumen file | `lumen-qwen3-fast-shared-q4_k_m.gguf` |
| File size | 1,282,439,264 bytes |
| File SHA-256 | `a7f6720f68f4a4567ebf7e3257041dd0b72077b518efe56890aec3516b59b9de` |
| Immediate source repository | `rippertnt/Qwen3-1.7B-Q4_K_M-GGUF` |
| Immediate source revision | `b93c0c328252f68cda622847ba0218689a8b6ba4` |
| Immediate source file | `qwen3-1.7b-q4_k_m.gguf` |
| Identified upstream base | `Qwen/Qwen3-1.7B` |
| Exact upstream Qwen revision used for quantization | **Not recorded** |

Pinned links: [Lumen artifact](https://huggingface.co/ales27pm/lumen-qwen3-bootstrap-gguf/blob/8abae6d695408dbc75a134212dd616cd14549ae1/lumen-qwen3-fast-shared-q4_k_m.gguf),
[immediate-source artifact](https://huggingface.co/rippertnt/Qwen3-1.7B-Q4_K_M-GGUF/blob/b93c0c328252f68cda622847ba0218689a8b6ba4/qwen3-1.7b-q4_k_m.gguf),
and [immediate-source card](https://huggingface.co/rippertnt/Qwen3-1.7B-Q4_K_M-GGUF/blob/b93c0c328252f68cda622847ba0218689a8b6ba4/README.md).

The Lumen file is byte-identical to the immediate-source file at the pinned
revision. Lumen only renamed and re-hosted that GGUF; it did not convert,
quantize, merge, or otherwise modify its bytes.

The immediate-source model card identifies `Qwen/Qwen3-1.7B` as the base,
declares Apache-2.0, and describes GGUF conversion with llama.cpp through the
GGUF-my-repo workflow. It does not record the immutable upstream Qwen commit
used for the April 2025 conversion, so this card does not invent one.

## Scope warning

This draft's byte-identity and provenance statements apply only to
`lumen-qwen3-fast-shared-q4_k_m.gguf`. The repository revision also contains
separate Lumen release-bake GGUF files. Those files are not the byte-identical
rehost documented here, and this draft does not establish their provenance or
license status. They require separate documentation before any repository-wide
licensing claim is made.

## Intended use

The covered artifact is intended as a local GGUF base for a compatible
llama.cpp runtime, including Lumen's role-adapter runtime. Model output is
untrusted and must remain behind application-layer validation, permissions,
approvals, privacy controls, and bounded tool execution.

## Limitations

- The exact upstream `Qwen/Qwen3-1.7B` revision used by the immediate-source
  quantizer is unknown.
- Quality, safety, and performance depend on the runtime, prompt, sampling
  configuration, device, and any applied adapters.
- This artifact is not itself an application safety or authorization system.

## License and attribution

The covered shared-base artifact is provided under the Apache License 2.0;
see `LICENSE`. See `NOTICE.md` for the immutable source chain, modification
statement, scope boundary, and attribution.

Alibaba Cloud, the Qwen authors, rippertnt, Hugging Face, llama.cpp,
GGUF-my-repo, and their respective contributors do not endorse Lumen, this
rehost, or applications that use it.