Kimi-K3-Cubic-2.5Bit is the first public showcase of Cubic quantization,
exploring practical ultra-low-bit, high-concurrency LLM inference.
Cubic uses parameterized, non-uniform levels that adapt to each weight group,
designed to challenge conventional integer and floating-point formats at
ultra-low precision while relaxing the usual need for small group sizes; most
quantized layers in this model use group size 512.
The export is fully data-free: no calibration dataset or activation samples
were used. The complete converter is included as
quantize_k3.py. The same packed checkpoint runs in either
weight-only A16 or dynamic-A8 mode through the
QuantTrio vLLM Cubic runtime.
This checkpoint itself uses mixed W2, W3, and W4 expert weights with an audited
effective width of 2.4986 bits.
【Quantization Policy】
Scope
Format
Dense layer 0
Source dtype (BF16)
MoE layers 1–3 routed experts
Cubic W3, group size 256
MoE layers 4–32 routed experts
Cubic W3, group size 512
MoE layers 33–91 routed experts
Cubic W2, group size 512
MoE layer 92 routed experts
Cubic W4, group size 512
Attention/KDA/MLA weights
Source dtype (BF16)
Shared experts and ordinary MLP weights
Source dtype (BF16)
Vision tower, multimodal projector, embeddings, norms, and LM head
Source dtype
Loss is the scale-free NRMSE of groupwise weight reconstruction, not a
downstream task-accuracy score.
The throughput values are stable decode-window measurements from short-prompt,
long-output text requests, rather than end-to-end request throughput. Prompt
length, generated context length, sampling, concurrent prefill, GPU clocks, and
other workloads can change the result. Because --max-model-len auto derives
the limit from free memory measured during startup, the effective token count
can also vary slightly between launches.
fp8_q16 is an optional query-preserving FP8 KV-cache mode from the Cubic
runtime. It keeps attention queries in the model dtype and automatically
selects a compatible attention backend. To use a conventional BF16 KV cache,
replace it with --kv-cache-dtype auto; this reduces the available context
length but provides the highest-precision KV storage.
The first launch may spend several minutes compiling Triton kernels,
calibrating Cubic kernel choices for the tensors and GPU type in use, and
capturing CUDA graphs. Calibration results are persisted in the Triton cache
and reused by later launches on compatible devices.
【Validation Status】
8 × H200 TP8 + EP model loading and text generation verified.
Weight-only A16 and dynamic-A8 execution verified with the same checkpoint.
fp8_q16 and BF16 KV-cache serving paths verified.
No formal downstream benchmark is claimed for this quantized checkpoint;
evaluate quality and performance for your own workloads before deployment.
This quantized checkpoint is derived from Kimi K3 and remains subject to the
Kimi K3 License.
The QuantTrio vLLM Cubic runtime is distributed separately under its own
repository license.
【Base Model Overview】
The following material is reproduced from the upstream Kimi K3 model card and
describes the base model. Upstream MXFP4 deployment instructions do not apply
to this Cubic checkpoint; use the Cubic installation and launch command above.
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window. It is the world's first open 3T-class model, designed for frontier intelligence across long-horizon coding, knowledge work, and reasoning.
Key Features
New Architecture: Kimi K3 is built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), and scales up MoE sparsity with a Stable LatentMoE framework that activates 16 out of 896 experts — yielding an approximate 2.5× improvement in overall scaling efficiency over Kimi K2.
Long-Horizon Coding: Operating with minimal human oversight, Kimi K3 sustains long engineering sessions, navigates massive repositories, and orchestrates terminal tools — from GPU kernel optimization and compiler development to vision-in-the-loop game dev, CAD, and even chip design.
Agentic Knowledge Work: Kimi K3 advances end-to-end knowledge work, producing deep research with interactive visualizations, widgets and dashboards, and motion design and video editing, powered by its native multimodal architecture.
Native Multimodality & Long Context: Kimi K3 understands text, images, and video within the same model, and supports a 1-million-token context window.
Open Frontier Weights: We release the full Kimi K3 model weights under the Kimi K3 License, making frontier intelligence openly available for research, deployment, and further innovation.
All Kimi K3 results are obtained with reasoning effort set to 'max' and temperature = 1.0. For single-step tasks, such as GPQA Diamond, HLE-Full, and vision benchmarks without tools, we set top-p = 0.95; for agentic tasks, we set top-p = 1.0. For HLE-Full, MMMU-Pro, CharXiv (RQ), MathVision, and ZeroBench, each cell reports the scores without and with tool augmentation (general tools for HLE-Full, Python for the vision benchmarks), in that order.
Reasoning & knowledge benchmarks
CritPt and AA-LCR. Scores are cited from Artificial Analysis as of July 23, 2026.
Coding benchmarks
DeepSWE. Kimi K3 is evaluated with the Kimi Code harness. The GLM-5.2 score is taken from the GLM-5.2 release blog; all remaining scores are from the official DeepSWE leaderboard, under which Kimi K3 attains 67.3 with the mini-SWE-agent harness. We report the DeepSWE v1.1 tasks.
Terminal-Bench 2.1. Kimi K3 is evaluated with the Kimi Code harness. For all other models, we report the best score across harnesses: GLM-5.2 with Claude Code (GLM-5.2 release blog); Claude Opus 4.8 and Claude Fable 5 with Terminus 2 (Artificial Analysis); GPT-5.5 and GPT-5.6 Sol with Codex (OpenAI).
ProgramBench. Kimi K3 is evaluated with the Kimi Code harness. The GLM-5.2 score is from the GLM-5.2 release blog; all other scores are from Vals AI.
SWE-Marathon. Kimi K3, Claude Opus 4.8, and Claude Fable 5 are evaluated with the Claude Code harness; GPT-5.6 Sol is evaluated with the Codex harness. The GLM-5.2 score is from the GLM-5.2 release blog. Our evaluation is based on an H20-calibrated branch of the official tasks as of July 9, 2026, prior to the final v1.1 release: the Docker images, performance gates, and reference oracles for the GPU tasks have been recalibrated for H20, while the correctness and anti-cheat validators remain unchanged. Additionally, Claude Fable 5 hit fallbacks on 35% of the tasks in our evaluation, which may have negatively impacted its measured performance.
FrontierSWE. Kimi K3 is evaluated with the Kimi Code harness and GPT-5.6 Sol with the Codex harness; all other results are from FrontierSWE. Dominance scores are recomputed from the raw scores using the official evaluation script and are current as of July 16, 2026.
PostTrainBench. Scores for GLM-5.2, GPT-5.5, and Claude Opus 4.8 are adopted from the official PostTrainBench results. Kimi K3, Claude Fable 5, and GPT-5.6 Sol are evaluated with the official Harbor implementation at maximum reasoning effort, averaged over three runs on H20 GPUs (instead of H100 in the official setting) — Kimi K3 and Claude Fable 5 with the Claude Code harness, and GPT-5.6 Sol with the Codex harness.
MLS-Bench-Lite. Kimi K3 is evaluated with the Kimi Code harness; GLM-5.2 and the Claude models with the Claude Code harness; GPT-5.5 and GPT-5.6 Sol with the Codex harness.
Kimi Code Bench 2.0 (in-house). Kimi K3 is evaluated with the Kimi Code harness (it attains 73.7 with the Claude Code harness); GLM-5.2, Claude Opus 4.8, and Claude Fable 5 with the Claude Code harness; GPT-5.5 and GPT-5.6 Sol with the Codex harness. All models are evaluated at maximum reasoning effort, except GPT-5.5, which uses the "xhigh" setting. As the benchmark includes cybersecurity and safety-related tasks, we also disclose the fraction of refused or fallback tasks: Claude Fable 5 hit 13 fallbacks and 1 refusal out of 80 tasks; 10 refusals out of 80 tasks entered GPT-5.6 Sol's cyber guard; GPT-5.5 had 3 refusals out of 80 tasks.
Agentic benchmarks
OfficeQA Pro. Each test case provides the agent with the entire PDF corpus, with all PDFs rendered as images and no machine-readable text available.
OfficeQA Pro and SpreadsheetBench 2. Kimi K3, GLM-5.2, Claude Opus 4.8, and Claude Fable 5 are evaluated with the Claude Code harness; GPT-5.5 and GPT-5.6 Sol are evaluated with the Codex harness.
MCP-Atlas. All models are evaluated on the 500-task public subset with a 100-turn limit, using Gemini 3.1 Pro as the judge.
AutomationBench. All models are evaluated on the 600-task public subset, following the official GitHub setup in all other respects.
BrowseComp. We adopt a context-compaction strategy triggered at 300K tokens. When evaluated with the full 1M-token context window and no context management, Kimi K3 achieves a score of 90.4. The results of Claude Fable 5, Claude Opus 4.8, GPT-5.6 Sol, and GPT-5.5 are cited from Anthropic and OpenAI.
GDPval-AA v2, AA-Briefcase, τ³-Banking, Harvey Lab-AA, and APEX-Agents. Scores are cited from Artificial Analysis and the APEX-Agents leaderboard as of July 23, 2026. For Harvey Lab-AA, we report the criterion pass rate.
CorpFin v2, Finance Agent v2, and Legal Research Bench. Scores are cited from Vals AI.
Agents' Last Exam. Scores are cited from the official leaderboard as of July 23, 2026; we report the leaderboard's primary pass-rate metric. On the leaderboard, each model is paired with a specific harness: Kimi K3 with Kimi Code; GPT-5.6 Sol and GPT-5.5 with Codex; Claude Fable 5, Claude Opus 4.8, and GLM-5.2 with Claude Code. † The Claude Fable 5 entry runs at xhigh effort with 40% of tasks annotated as downgraded.
Multimodal benchmarks
Except for ZeroBench, which follows the official setting and is run five times, all multimodal scores are averaged over three runs. MMMU-Pro is evaluated following the official protocol, preserving the original input order and prepending images to the text input.
PerceptionBench is an in-house benchmark that focuses on atomic visual perception capabilities.
4. Native MXFP4 Quantization
Kimi K3 applies quantization-aware training from the SFT stage onward, using MXFP4 weights with MXFP8 activations for broad hardware compatibility.
5. Deployment
[!Note]
You can access Kimi K3's API on https://platform.kimi.ai by selecting kimi-k3, and we provide OpenAI/Anthropic-compatible API for you. Currently, Kimi K3 is recommended to run on the following inference engines:
Kimi K3 always has thinking enabled, and will return reasoning_content. Thinking effort is configured with the top-level reasoning_effort request field, which supports "low", "high", and "max" (default "max").
Kimi K3 was trained in the preserved thinking history mode. For multi-turn conversations and tool calls, Kimi K3 requires the complete assistant message returned by the API to be passed back to messages as-is — including reasoning_content and tool_calls, not just content:
python
1import openai
23defchat_with_preserved_thinking(client: openai.OpenAI, model_name:str):4 messages =[5{6"role":"user",7"content":"Tell me three random numbers."8},9{10"role":"assistant",11"reasoning_content":"I'll start by listing five numbers: 473, 921, 235, 215, 222, and I'll tell you the first three.",12"content":"473, 921, 235"13},14{15"role":"user",16"content":"What are the other two numbers you have in mind?"17}18]1920 response = client.chat.completions.create(21 model=model_name,22 messages=messages,23 stream=False,24 max_tokens=4096,25 reasoning_effort="max",26)27# the assistant should mention 215 and 222 that appear in the prior reasoning content28print(f"response: {response.choices[0].message.reasoning}")29return response.choices[0].message.content
For full guides and examples (vision input, structured output, partial mode, tool choice, dynamic tool loading, context caching), see the Kimi K3 Quickstart and Thinking Effort.
Coding Agent Framework
Kimi K3 works best with Kimi Code CLI as its agent framework. We warmly invite you to give it a try — run Kimi Code in your terminal and select Kimi K3 using the /model command. We hope you enjoy building with Kimi K3, and we would love to hear your feedback!
7. License
Both the code repository and the model weights are released under the Kimi K3 License.
){kind=icon}
