turintech/gemma-4-E2B-it-Artemis-GGUF
image-text-to-text model by turintech
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.
TurinTech models, built with Artemis Google's Gemma 4 E2B for chat and tool calls on a CPU, compressed with Artemis from the QAT checkpoint Ollama: ollama run turintech/gemma-4-e2b-it-artemis · LM Studio: turintech/gemma-4-e2b-it-artemis Needs llama.cpp with Gemma 4 support (the Results table and the memory figures were measured with b11617; the projector and the MTP drafter were converted, checked and measured with b11889). Without --no-mmproj, -hf also downloads the 986 MB vision projector and loads it (images, below). -np 1 keeps one slot and --cache-ram 0 turns off llama-server's prompt cache in RAM (8 GiB by default): the 3.6 GiB of CPU memory on this card was measured that way, text only, and with the default cache memory grew to 11.8 GiB over the full task suite. The chat template turns thinking on by default: the server returns it in message.reasoningcontent and the answer in message.content, so allow enough output tokens…
Read the full model card ↗ · Preview checked 2026-11-17T07:13:07.971Z
Inside the original model card — Document outline
- Run it
- Results
- Files
- Pick this model
- How it was made
- How it was tested
- Closeness to the original
- Protocol ryzen5900x-2026-10-20
- Protocol ryzen9950x-2026-10-12
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
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
turintech/gemma-4-E2B-it-Artemis-GGUF is a image-text-to-text model repository published by turintech on Hugging Face. The source reports the gguf 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
- gguf
- Recent downloads (30 days)
- 786,363
- Cumulative likes
- 15
- Hugging Face trending score
- 1
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-12T20:52:18.000Z
- Last modified
- 2026-11-16T12:08:35.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: google/gemma-4-E2B-it-qat-q4_0-unquantized
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 2026-11-17T07:02:07.416Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.