ornith-ai · qwen3_5
Ornith-1.5-9B-NVFP4
Ornith-1.5-9B-NVFP4 by ornith-ai: a 6.7B-parameter dense open-weight model under the mit license with tool calling and vision.
1,144,071 downloads · 34 likes · Model card · synced 2026-11-19
Specifications
- Parameters
- 6.7B
- Architecture
- dense · qwen3_5
- Layers
- 32
- Hidden size
- 4,096
- KV heads · head dim
- 4 · 256
- Vocabulary
- 248,320
- Native dtype
- —
- Context window
- 262,144 tokens
- Released
- 2026-08-26
- Last modified on Hub
- 2026-08-26
Features & licensing
- License
- mit
- Commercial use
- Yes
- Modalities
- text, vision
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Languages
- EN
- Quantised variants on Hub
- GGUF
- Pipeline
- text-generation
Task fit
Editorial scores (0–100) used by the recommendation engine.
- Chat70
- RAG / Q&A70
- Code70
- Summarisation70
- Extraction70
- Agents70
Hardware to run Ornith-1.5-9B-NVFP4
Weights need about 15 GB at FP16, 8 GB at INT8 and 4 GB at INT4. The KV cache adds roughly 131 MB per 1,000 tokens per request. For a reference workload of 5 requests per second with 1,500 input and 300 output tokens, total GPU memory is around 6.4 GB, which fits on 1 × NVIDIA A100 (80 GB).
| Configuration | VRAM | Utilisation | Est. first token | Cloud / month |
|---|---|---|---|---|
| 1 × NVIDIA L4 (24 GB) | 24 GB | 27 % | ~0.5 s | $584 |
| 1 × NVIDIA L40S (48 GB) | 48 GB | 13 % | ~0.2 s | $1,387 |
| 1 × NVIDIA A100 (80 GB)recommended | 80 GB | 8 % | ~0.1 s | $2,336 |
| 1 × NVIDIA H100 (80 GB) | 80 GB | 8 % | ~0.0 s | $3,285 |
Estimates only. Run an assessment for your own traffic.
Auto-imported from Hugging Face. Architecture, license and feature data are synced from the model repository; the task-fit scores below are provisional defaults until a curator reviews them.