AltAPIs

keptn/ornith-1.5-122b-w4a8

AI model by keptn

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

ornith-ai/Ornith-1.5-122B in one 64.6 GiB file for the radiance inference engine on AMD RDNA4. 4-bit experts make it fit on four 32 GB cards without host memory, with room for 8 sequences at full length. A second file with the DFlash2 drafter instead of MTP is in keptn/ornith-1.5-122b-w4a8-dflash2. See "MTP or DFlash2" below. The official image is stilldeadcode/radiance:1.11.0. Then: Distance to the bf16 original. KL divergence on wikitext-2 (test), llama.cpp method: 100 chunks of 512 tokens, the second half of each chunk scored, 25,500 tokens. Reference: the bf16 original in HF transformers, fp32 math. Benchmarks, greedy. The thinking-off column is the one to compare with other cards. Radeon AI PRO R9700 at 215 W, radiance 1.9.0 + PR #144, fp8 KV, 3 draft tokens, thinking off. BetterBench 0.6.1, full run: 8 categories, 20 runs each after 3 warm-up runs, temperature 0.7, one stream. Then prefill and parallel streams. Decode tok/s…

keptn/ornith-1.5-122b-w4a8 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-29T11:53:46.698Z

Inside the original model card — Document outline
  1. Ornith 1.5 122B · w4a8 · for radiance
  2. Quick start
  3. Quality
  4. Speed
  5. Vision
  6. Memory
  7. MTP or DFlash2
  8. How it was made
  9. Limits
  10. Credits
  11. License

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. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

keptn/ornith-1.5-122b-w4a8 is a task-unspecified model repository published by keptn on Hugging Face. A library was not reported.

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
Not reported
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
Not reported — check the model card
Access
Not gated by Hugging Face
Created
2026-10-22T06:19:23.000Z
Last modified
2026-10-22T06:19:23.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

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.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-10-22T06:45:03.943Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models