theatechcorporation/amaara-code-20b-r7-GGUF
AI model by theatechcorporation
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.
Experimental GGUF quantisations of Amaara Code 20B r7, a coding-agent fine-tune of openai/gpt-oss-20b (≈21B total / ≈3.6B active MoE). All sizes render from the same canonical conversation store. Only the chat template differs per architecture (Harmony here, Qwen ChatML for the 4B, GLM for Amaara Code Flash), so cross-size comparisons are attributable to the model rather than to the data. Selection is by trajectory shape: verified edit→test→pass and self-correction traces are kept; unverified edit-and-stop traces are dropped; long traces are windowed around the edit→verify tail rather than discarded. Q80 is the fidelity reference. Lower quants trade accuracy for VRAM; pick the largest that fits your device. gpt-oss keeps a large number of tensors at F32, so file sizes are larger than…
Read the full model card ↗ · Preview checked 2026-11-22T09:20:36.084Z
Inside the original model card — Document outline
- Amaara Code 20B r7 — GGUF
- One corpus across every Amaara Code model
- Files
- Evaluation
- Licence
- Join the AI Owner's Club
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: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
theatechcorporation/amaara-code-20b-r7-GGUF is a task-unspecified model repository published by theatechcorporation on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- Not reported
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-11-22T06:15:30.000Z
- Last modified
- 2026-11-22T06:25:20.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: openai/gpt-oss-20b
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 2026-11-22T07:03:33.420Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.