Open-Weight Models

Model · Text classification

Darwin-27B-ZTC-v2

FINAL_Bench

A zero-token decision engine from the Darwin family, second version. Darwin-27B-ZTC-v2 reads a piece of state and a typed question (noul yes or no, choice one of N labels, score an ordered rubric) and returns a probability for every option. It uses one forward pass per question and generates no tokens. v2 adds control and workflow decisions (games, drones, retrieval control, entity alignment, customer and incident workflows) on top of FINAL-Bench/Darwin-27B-ZTC. 1 on the S1MB leaderboard under both of its rankings: the default Borda score and Task Avg. All 137 benchmarks complete, measured with the S1MB evaluator and its autojev adapter at revision a8f283a, then validated and merged by the…

static quants of https://huggingface.co/SII-Enigma/Davinci-Tool-30B

weighted/imatrix quants of https://huggingface.co/SII-Enigma/Davinci-Tool-30B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Davinci-Tool-30B-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…

Decider-4B is a structured decision model based on TokenRhythm/NeoHorse-1-4B. It uses LoRA to fine-tune the base model and trains the decision head from scratch on our collected decision datasets. The model then undergoes global temperature calibration to further calibrate its outputs. It produces typed probability distributions (noul, choice, score) and is not a chat-generation model. Exact run settings, where recorded by the exporter, are retained in modelmanifest.json; reference scripts under provenance/recipereference/ describe the project recipes rather than prove the exact mixture or hyperparameters of this checkpoint. No additional head-only training phase is claimed for this…

Decily scores a runtime-provided set of candidates against a state and a question, and returns a calibrated probability distribution over those candidates. It does not generate text. Decily is built for decisions where you want a probability you can threshold, not a sentence you have to parse. Apple MLX 4-bit build — the on-device variant. The tower is quantized (group-64 affine, 968 MB); the scoring head ships separately in decisionhead.safetensors (kept in fp32 for calibration). This card covers all four released artifacts; they are the same model in different containers. state + question + candidate jointly; an attention-pooling layer over all tokens feeds a LayerNorm/GELU MLP that…

Decily scores a runtime-provided set of candidates against a state and a question, and returns a calibrated probability distribution over those candidates. It does not generate text. Decily is built for decisions where you want a probability you can threshold, not a sentence you have to parse. ONNX int8 build (1.66 GB, single self-contained file) — the CPU/edge artifact. Dynamic int8 quantization of the full scoring graph (inputids + attentionmask -> logits); PyTorch is not needed to run it. Each row is one candidate's state + question + candidate token sequence; the logits are softmaxed over the candidates. Reference runner: fair-suite parity batch; the fp32 graph matches (Apple M5 CPU, 4…

Model · Text generation

Decision-1-NF4

Worthify AI

A pre-quantized NF4 checkpoint in the Worthify Decision-1 family. Download 7.64 GB of weight shards and load the saved NF4 tensors directly. In three short usage checks on an RTX 3090, peak PyTorch-allocated inference memory was 7.26 GiB. We converted Decision-1 at cab55818cfb6f4163f2b2597bed31cceb6ba2030 with bitsandbytes NF4 and double quantization. This release adds no training. Decision-1 is a single-seed research preview derived from Gemma 4 12B; its original model card describes the training and BF16 evaluation. Give the model a text state, a question, and 2–16 described options. Read the next-token scores for the supplied option letters to select an option ID. Those scores are…

Model · Text classification

Decision-1.0-Kai-0.6B

vLLM Semantic Router

Kai, from kairos — the right moment to choose. Open Decision Foundation Models Choose an action, judge a condition, or score against your own rubric. Kai reads the context and candidate descriptions together, then returns structured decisions and probability distributions. 53.52 overall — above both general Laya models, and +7.04 points over the previous Kai release. On the benchmark's 160-question BoolQ slice, Kai scores 74.38%, versus 69.38% for each Laya reference. Same 54 tasks and 3,766 scored questions, with fixed source/family weights. Both Laya references use released general weights, without target-dataset fine-tuning. This is an observed regression suite; results vary by task.…

Model · Text classification

Decision-1.0-Lex-0.6B

vLLM Semantic Router

Lex — Latin for law. Give your decisions a rule. Open Decision Foundation Models Turn operational context into structured decisions. Lex is a specialist fine-tuned from Kai to select actions, test conditions and apply scoring rubrics across four operational workflows. 78.15% accuracy — 1.55 points above Laya Typed Decisions. Lex contains 571,909,635 parameters. Both models were evaluated on the original 2,000-decision English typed-decisions test split, with complete inputs and the official fine-tuned Laya checkpoint. Lex answers 31 more decisions correctly. Observed accuracy gain; the paired 95% interval is −0.20 to +3.15 points. Laya leads on Noul and probability-quality metrics. Full…

weighted/imatrix quants of https://huggingface.co/richardyoung/DeepSeek-R1-0528-Qwen3-8B-heretic For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…

This model was quantized using oQ (oMLX v0.7.0) mixed-precision quantization.

Model

DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16

MAXLABS

This model was quantized using oQ (oMLX v0.7.0rc1) mixed-precision quantization.

We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations…

DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached. DeepSeek-V4-Pro-0813 outperforms DeepSeek-V4-Pro (Preview) on the benchmarks listed below, and is broadly competitive with the strongest proprietary models available. 1. For the code-agent tasks among the public benchmarks above, DeepSeek-V4-Pro-0813 is evaluated with the minimal mode of DeepSeek Harness as the agent framework, using the max reasoning…