| --- |
| license: other |
| license_name: mistral-modified-mit |
| license_link: LICENSE |
| base_model: |
| - mistralai/Timestral-5M |
| - mistralai/Timestral-28M |
| - mistralai/Timestral-123M |
| - mistralai/Timestral-209M |
| base_model_relation: quantized |
| library_name: timestral.cpp |
| tags: |
| - gguf |
| - time-series |
| - forecasting |
| - timestral |
| --- |
| # Timestral GGUF models for timestral.cpp |
|
|
| This interim release contains fourteen GGUF files for native CPU forecasting with [timestral.cpp](https://github.com/mudler/timestral.cpp). |
| Inference requires no Python or libtorch. Conversion uses the pinned upstream checkpoints listed in `manifest.json`. |
|
|
| ## Available models |
|
|
| | Directory | Available formats | Validation | |
| | --- | --- | --- | |
| | `5M/` | F32, F16, Q8_0 | All three pass storage, schema, lineage, and byte-encoding audits. F32 passes trained parity; reduced-format forecast quality is not yet evaluated. | |
| | `28M/` | F32, F16, Q8_0 | Storage, schema, source-byte association, RoPE, and encoding audits pass. Native inference and forecast quality remain pending. | |
| | `123M/` | F32, F16 | Storage, schema, source-byte association, RoPE, and encoding audits pass. Native inference and forecast quality remain pending. | |
| | `209M/` | F32, F16, Q8_0, Q6_K, Q5_K, Q4_K | All six pass cohort/storage admission. Full quality evaluation completes, but the Q8 mean-deviation gate fails. | |
|
|
| All four upstream models now have converted artifacts in this repository. Native qualification is incomplete for 28M and 123M. |
| 123M Q8_0 is unavailable: its 1712-wide FFN matrices do not satisfy the unchanged 32-value block requirement. |
| K formats for 5M, 28M, and 123M are incompatible with the unchanged complete weight policy. No padding or selective exclusions are used. |
| |
| ## Quality and performance limitations |
| |
| The qualified optional standalone MKL profile uses runtime `68a5a53` and the documented SDK version. |
| Results do not establish parity or quality for every backend, SDK, or machine. |
| No proprietary SDK libraries are included here. |
| |
| The 209M quality evaluation covers 79 items, six formats, 474 native calls, and 79 fresh F32 anchor pairs. |
| All formats have complete coverage. Immutable closing checks pass. |
| |
| | 209M format | Aggregate mean normalized deviation from F32 | Absolute aggregate WQL change | |
| | --- | ---: | ---: | |
| | F32 | 0 | 0% | |
| | F16 | 0.00015529176950670028 | 0.00274317535567626% | |
| | Q8_0 | 0.005657737466196431 | 0.04116458747472307% | |
| | Q6_K | 0.013512040093425381 | 0.06180385023158404% | |
| | Q5_K | 0.02008887882387394 | 1.3580854256823647% | |
| | Q4_K | 0.033048053192290705 | 2.770376555053301% | |
| |
| F16 passes its mean-deviation bound of 0.001 and WQL-change bound of 0.5%. |
| **Q8_0 fails its mean-deviation bound of 0.005.** Its WQL change passes the 1% bound. |
| WQL changes above are already percentages. Normalized deviation is not raw percentage forecast error. |
| Strict mean-error ordering passes. K formats have no separate loss bound in this contract. |
| MASE degeneracies remain reported, not excluded. |
| |
| **Formal latency acceptance fails at both tested thread counts.** Memory bounds pass. |
| Review and optimization remain pending. This interim publication does not waive any acceptance gate. |
| |
| See the [complete quality report](https://github.com/mudler/timestral.cpp/blob/a4a1f95bb993a364c59d66edea17dafb2f17522a/docs/quantization-209m-result.md), |
| [F32 replay](https://github.com/mudler/timestral.cpp/blob/a4a1f95bb993a364c59d66edea17dafb2f17522a/docs/coherent-f32-replay.md), |
| and [runtime documentation](https://github.com/mudler/timestral.cpp/blob/a4a1f95bb993a364c59d66edea17dafb2f17522a/docs/standalone-mkl.md). |
| Use the native CLI or C ABI documented in the code repository. GGUF storage does not imply compatibility with unrelated GGUF runtimes. |
| |
| ## Licence |
| |
| These weights use Mistral AI's **Modified MIT License**, not unrestricted MIT. |
| Read the complete [original licence](LICENSE), including its attribution, disclaimer, and revenue restriction. |
| The licence restricts rights when your company or employer exceeds USD 20 million in consolidated monthly revenue for the preceding month. |
| The restriction also covers derivatives. Contact Mistral AI for a commercial licence when required. |
| Keep the original notices with copies and derivatives. This repository does not grant additional rights. |
| |
| ## Integrity and provenance |
| |
| `manifest.json` records exact sizes, SHA-256 hashes, upstream revisions, and runtime/reference identities. |
| `SHA256SUMS` contains checksums for all fourteen GGUF files. |
| F32/F16/Q8_0 use the pinned converter; 209M K formats use the reviewed native quantizer. |
| The 5M F32 file is byte-identical to the previously accepted trained-parity artifact. |
|
|
