Model overview
GGUF builds of `ornith-ai/Ornith-1.5-9B` with a **distilled MTP draft head baked into the trunk** — llama.cpp does lossless multi-token self-speculative decoding out of the box, no separate draft model to wire up. Every file here carries the `nextn` head, so `--spec-type draft-mtp` just works. Ornith ships 1.5-9B with `mtp_num_hidden_layers: 1` in `config.json` but **none of the `mtp.*` weights** — 0 of 760 tensors. So the stock GGUFs (official and third-party) have no MTP head and can't speculate. These do. > **`Q4_K_M` is no longer the low-VRAM recommendation.** An earlier version of this card said it > was. `IQ4_XS` beats it on size, speed and MTP gain — measured, table below.
Key features
特点摘要待依据来源补齐，不凭模型名称推断能力。
Limitations & considerations
Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.
Source prices & cost analysis
Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.
| Source / channel | Input | Output | Billing unit | Collected at |
|---|---|---|---|---|
| No verified prices yet. Check the source channel. | ||||
Estimate monthly base token costs
Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.
Public benchmarks & run configuration
暂无已采集的可核验公开评分。模型未上榜不代表能力较低。
View full indexed rankings →Frequently asked questions
Do open weights permit free commercial use?
Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.
Are these real-time billing prices?
These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.
Sources & traceability
许可证：mit。模型介绍与第三方评测均以原来源的具体版本和方法为准。