Kimi K3 vs ZAYA1-8B

Kimi K3 50

Memory earns nothing, because the only build of 4-bit precision or better from Moonshot or a runtime's own library is Moonshot's MXFP4 release of 1,561 GB, about 1,873 GB with the fifth added, far above 256 GB. Ollama and LM Studio list it only as a cloud model. Runtimes earn 15, for model code in released vLLM, SGLang and llama.cpp; Transformers has no kimi_k3 code of its own and loads Moonshot's remote code, so it doesn't count. Builds earn 10 for one publisher precision, the MXFP4 files the model was trained for. Terms earn 10, a custom MIT-based licence that is free for commercial use below a revenue threshold. Download earns 10, with no gate and no account. Hosted earns 5, since Moonshot's API serves it and five inference providers are live for it on Hugging Face.

ZAYA1-8B 80

Memory 30, the smallest build from Zyphra is the MXFP4-Experts repository, 5.85 GB, and 5.85 GB × 1.2 = 7.0 GB, within 16 GB. Runtimes 10, Released Transformers 5.22.2 has the zaya model and SGLang 0.5.23 has srt/models/zaya.py. Builds 15, Quantised builds from Zyphra at two precisions, FP8 and MXFP4 for the experts, each in its own repository. Terms 15, Apache 2.0 in the card's metadata, an OSI licence with nothing added. Download 10, the Hub API reports gated false for the model and its builds on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it, and the card names no API. Zyphra's site lists a cloud product for its open models, which wasn't checked for this model. 30 + 10 + 15 + 15 + 10 + 0 = 80.

Kimi K3 65

File safety earns 15, safetensors only with no pickle files, less 10 because the documented loading path runs Moonshot's Python with trust_remote_code and builds prompts with encoding_k3.py. Provenance earns the full 15, files in the organisation Moonshot links to with a SHA-256 for every shard. Safety evaluation earns 20 for the cyber assessment the UK AI Security Institute and CAISI ran and published, which found its safeguards didn't stop exploit development. Agent guidance earns 5 for the blog's general cautions about proactiveness and passing back thinking. Licence risk earns 10, losing 5 for the model-as-a-service revenue threshold and nothing else. The security programme earns nothing, with no security.txt, disclosure policy, SECURITY.md or public advisories found.

ZAYA1-8B 55

File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in the Zyphra organisation, which the card ties to zyphra.com's blog post for the model (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 0, no way to report a flaw on the card, and www.zyphra.com has no security.txt. 25 + 15 + 0 + 0 + 15 + 0 = 55.

Kimi K3 41

The model card earns 11, covering intended use, architecture, parameters and context, but not limitations, languages or a knowledge cut-off. Training data earns 5 for a general description with no cut-off. The last change earns 15, an encoding_k3.py update on 20 August, 74 days before 2 November and within 90; the GitHub repository's last commit is 6 August. Responsiveness earns nothing, with no Moonshot reply in the 40 most recent discussions. Version policy earns 5 for a first release. File health earns 5, because a report that the tokeniser goes past the declared vocabulary waits without a reply.

ZAYA1-8B 50

Model card 5, Intended use and the parameter counts are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the main repository last changed on 26 June 2026 (the checkpoint reshaped for Transformers), 137 days before this check, and the quantised repositories on 2 July, 131 days. Responsiveness 20, Of the 16 most recent discussions that aren't pull requests (7 May to 14 August 2026), 10 have a reply from a Zyphra member, which is most. Version policy 5, the original checkpoint is kept as ZAYA1-8B-legacy and the card says so at the top, without a date. File health 10, Config, template and card agree on the architecture after the reshape. 5 + 0 + 10 + 20 + 5 + 10 = 50.

Kimi K3 65

The chat template earns 10, because there is no Jinja template and the prompt format exists only as encoding_k3.py, code you run. The tool-calling format earns 10, since Moonshot documents the tools channel but the parser name comes only from vLLM's and SGLang's own recipes. Trained tool calling earns 20 for indexed parallel calls in one turn. Structured output earns 5, as the card names it among its linked guides without saying how to ask the weights for it, and the how sits in hosted-API docs. Reasoning control earns 10, with per-request effort documented on the card and reasoning returned as reasoning_content. Context earns 10 for 1,048,576 tokens trained in.

ZAYA1-8B 60

Chat template 20, chat_template.jinja in the repository (10,700 characters). Tool-calling format 10, only the template and a fork say it. Trained tool calling 10, the template takes tools and renders calls, and the card recommends settings for agent use, but it doesn't say the model was trained for tool calling or for several calls in a turn, so the lower band. Structured output 0, Nothing on the card about JSON or schema-constrained output. Reasoning control 10, the template has an enable_thinking switch, and the card names the qwen3 reasoning parser, which returns the reasoning apart from the answer. Context 10, 131,072 positions in config.json, for an architecture Zyphra trained end to end, so the config is the model's own. 20 + 10 + 10 + 0 + 10 + 10 = 60.