Model reference · open weights
Kimi-Linear is an open-weight language model from moonshotai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Overview Kimi Linear is a hybrid linear attention architecture that outperforms traditional full attention methods across various contexts, including short, long, and reinforcement learning (RL) scaling regimes. At its core is Kimi Delta Attention (KDA)—a refined version of Gated DeltaNet that introduces a more efficient gating mechanism to optimize the use of finite-state RNN memory. Kimi Linear achieves superior performance and hardware efficiency, especially for long-context tasks. It reduces the need for large KV caches by up to 75% and boosts decoding throughput by up to $6\times$ for contexts as long as 1M tokens. We open-source the KDA kernel in FLA, and release two versions model checkpoints trained with 5.7T tokens. Key Features - Kimi Delta Attention (KDA): A linear attention mechanism that refines the gated delta rule with finegrained gating. - Hybrid Architecture: A 3:1 KDA-to-global MLA ratio reduces memory usage while maintaining or surpassing the quality of full attention. - Superior Performance: Outperforms full attention in a variety of tasks, including long-context and RL-style benchmarks on 1.4T token training runs with fair comparisons. - High Throughput: Achieves up to 6× faster decoding and significantly reduces time per output token (TPOT). Usage Inference with Hugging Face Transformers To use the Kimi Linear model, we recommend the following environment: python = 3.10 torch = 2.6 fla-core = 0.4.0 Example Code: Deployment For deployment, you can use the latest vllm to create an OpenAI-compatible API endpoint. Citation If you found our work useful, please cite
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | moonshotai |
|---|---|
| Type | Language models |
| Parameters (lead) | 49.1B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2025-10-30 |
| Popularity | 181k downloads / month |
| Likes | 588 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Kimi-Linear-48B-A3B-Instruct | 49.1B | BF16 | ~113 GB | — | Weights ↗ |
Using it via the API
Once AxForge deploys kimi-linear for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (kimi-linear below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"kimi-linear","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Sources