3hs4n/MiniCPM-V-4.7-1B-mlx-mixed-4bit-8bit-compact
image-text-to-text model by 3hs4n
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Community native MLX conversion of OpenBMB MiniCPM-V-4.7-1B. Architecture, tokenizer, chat template and visual processing modes are retained. This repository provides the mixed 4-bit and 8-bit compact weights. Comparison tables include other profiles evaluated with the same setup. Runtime corrections are required; follow the setup instructions before loading the model. For the profile with stronger accuracy evidence in the limited checks, see the 8-bit compact model. Existing 4-bit language weights are retained byte for byte. Embeddings and the output head use affine 8-bit quantization with groups of 32. Vision weights, visual mergers and linear-attention weights remain at their original precision. Unchanged tensors were verified individually by SHA-256. Details are in conversion.json. The 8-bit compact weights occupy 2,375,477,210 bytes; the mixed compact weights occupy 2,221,336,424 bytes. These packages can be smaller than the community 4-bit baseline because they compress the embeddings and output head, which the baseline retains in BF16. The table…
Read the full model card ↗ · Preview checked 2026-10-31T05:50:20.441Z
Inside the original model card — Document outline
- MiniCPM-V 4.7 1B: mixed 4-bit and 8-bit compact
- Package size
- Runtime compatibility
- Platform scope
- Tool-free correctness comparison
- Unsloth GUI smoke check
- Mac text benchmark
- Precision and image detail
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
3hs4n/MiniCPM-V-4.7-1B-mlx-mixed-4bit-8bit-compact is a image-text-to-text model repository published by 3hs4n on Hugging Face. The source reports the mlx library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- mlx
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 1,554,476,272
- Architecture
- MiniCPMV4_7ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-14T06:11:37.000Z
- Last modified
- 2026-10-14T06:12:17.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: openbmb/MiniCPM-V-4.7-1B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-14T06:42:09.182Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.