ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Moonshot Kimi
Open-Weight Moonshot Kimi · MoE 2.78T / A104B · Text+Image+Video · BF16 / FP8

Kimi K3.1 Pro (2.8T MoE) Architecture Parameters, Benchmarks & VRAM

Moonshot October 2026 flagship 2.78T MoE (93 layers, 896 experts) with 1M input & 1M output context.

🧬 Kimi K3.1 Pro (2.8T MoE) Architecture & Tensor Specifications

Verified directly against HuggingFace (moonshotai/Kimi-K3.1-Pro) config.json & Model Card

HF Class: KimiK31ForConditionalGeneration

1. Backbone & Dimensions

kimi_k31
Total / Active Params
2.78T / 104B
Hidden Size (d_model)
7,168
FFN Intermediate Size
33,792
MoE Expert Dim
3,072
MoE Experts
896 Routed · Top-50 + 2 Shared
Activation / Norm
SiLU (SwiGLU) · ε=0.00001
Native Tensor Dtype
BF16 / FP8

2. Attention & Layer Layout

MLA
Num Hidden Layers
93 Layers
Hidden Layer Layout
93-Layer Sparse MoE (896 Experts, Top-50 Active)
Attention Heads (Q / KV)
96 Q / 96 KV
Head Dimension
75

3. Context, RoPE & Tokenizer

Tokenizer
Native Context Length
1,048,576 tokens
RoPE Configuration
RoPE (原生 1,048,576 Context)
Vocab Size
163,840 (Untied)

📋 Kimi K3.1 Pro (2.8T MoE) Official API & System Card Specifications

Verified against official Moonshot Kimi developer documentation & pricing

API Model ID: kimi-k3.1-pro

1. Identity & Capabilities

API Spec
API Model ID
kimi-k3.1-pro
Release Date
2026-10-23
Weight License
Open-Weight (API Spec)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,024,000 tokens (1024K)
Max Output Tokens
1,049,000 tokens
Input Modalities
Text + Image + Video
Output Modalities
Text
Direct China Access
✅ Direct CN + RMB
Deployment Mode
Open-Weight + Cloud API

3. Official Pricing & Cache

CNY / 1M
Input / 1M Tokens
¥ 13
Cached Input / 1M
¥ 1.3 -90%
Output / 1M Tokens
¥ 68
Tiered Pricing Notes
Moonshot AI: Moonshot AI official CN platform with auto prefix cache

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Default Sampling
temperature=0.7 top_p=0.95 max_tokens=32,768

📊 Kimi K3.1 Pro (2.8T MoE) Full Benchmark Scorecard

30 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

💻 Coding 10 items

BenchCAD (with Python tool) #4/8 92.7%

BenchCAD variant evaluated with access to a Python tool for programmatic CAD reasoning.

Kimi Code Bench v2 #1/3 77.1%

Kimi Code Bench v2 is Moonshot AI's in-house benchmark for evaluating coding agents on realistic software engineering tasks across 10+ mainstream programming languages and a production tech stack spanning backend services, infrastructure, performance engineering, systems…

DeepSWE #1/12 75.5%

DeepSWE is a software engineering agent benchmark evaluated with the mini-swe-agent harness, where each task is solved in an isolated container with no internet access. It measures an agent's ability to autonomously resolve real-world coding issues end to end.

ExploitBench #5/11 74.7%

ExploitBench is a cybersecurity benchmark that evaluates a model's ability to discover and exploit software vulnerabilities, reported as the fraction of challenges where the model captures the target (Cap%).

BenchCAD #3/8 72.8%

BenchCAD is a benchmark for programmatic CAD reasoning built from 17,900 execution-verified CadQuery programs spanning 106 industrial part families, roughly half anchored to real ISO, DIN, EN, ASME, and IEC specification tables.

Terminal-Bench 4.0 #4/31 65.7%

Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.

SWE-Marathon #2/9 51.7%

SWE-Marathon is an ultra-long-horizon software engineering benchmark covering tasks such as building compilers, optimizing kernels, and developing production-grade services. It measures whether agents can sustain quality across extremely long engineering trajectories.

Terminal-Bench-Science 0.1 #14/16 38.1%

Terminal-Bench-Science 0.1 is a Stanford-led community benchmark of 70 tasks drawn from scientific research workflows across the life, physical, earth, mathematical, and engineering sciences.

PostTrainBench #6/10 36.5%

PostTrainBench evaluates a model's ability to autonomously post-train base models. Given pretrain-only base models, the agent must complete the full pipeline of data synthesis, training, evaluation, and iteration within a time budget, scored across downstream benchmarks such as…

ExploitGym #5/9 20.7%

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities across userspace programs, Google's V8 engine, and the Linux kernel.

🤖 Agents & Tools 8 items

BrowseComp #1/54 92.1%

BrowseComp is a benchmark comprising 1,266 questions that challenge AI agents to persistently navigate the internet in search of hard-to-find, entangled information.

AutomationBench-AA #1/3 73.3%

AutomationBench-AA is Artificial Analysis's independently run version of AutomationBench, covering 657 real-world SaaS workflow tasks across 40 simulated applications (e.g. Gmail, Slack, Salesforce, HubSpot).

OfficeQA Pro #5/15 67.4%

OfficeQA Pro evaluates AI models on professional knowledge-work questions and tasks drawn from real office workflows, including document analysis, spreadsheet reasoning, and information synthesis across business domains.

APEX-Agents #2/15 67.2%

APEX-Agents is a benchmark evaluating AI agents on long horizon professional tasks that require sustained reasoning, planning, and execution across complex multi-step workflows.

GDPval-AA 2.1 #1/7 1846

Version 2.1 of the Artificial Analysis GDPval evaluation of professional knowledge work, reported as an Elo rating.

AA-Briefcase v1.1 #4/7 1678

AA-Briefcase v1.1 evaluates multi-hour professional office work and reports Elo scores. Kept separate from unversioned AA-Briefcase results.

Agents' Last Exam #15/29 43.2%

Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.

Harvey's Legal Agent Benchmark #1/5 23.7%

Harvey's Legal Agent Benchmark evaluates AI agents on complex legal workflows and reports the all-pass rate.

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

⚡ Kimi K3.1 Pro (2.8T MoE) Interactive VRAM & Token Speed Calculator

Concurrency (Batch):
MoE 2780B / A104B·93L (d=7168)·96Q/96KV·Ctx 1M·Text+Image+Video
Runnable Models →
GPUs
96 GB VRAM·4000 GB/s·Safe Usable 94.1 GB
Out of VRAM (OOM)1722.14 / 94.1 GBOOM
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Out of VRAM (OOM)
1722.14/ 94.1 GB usable

Physical 96 GB · Load 1830.5%

Theoretical Decode Speed
—tokens/s

Exceeds usable VRAM by 1628.06 GB

Max Context at Batch=1
0K/ 1M

MLA compresses multi-batch KV footprint

Weights: 1685.37 GBKV Cache (1×16K): 1.76 GBOverhead: 35.01 GB
⛔ Cannot Load
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run kimi-k3-1-pro-2800b

Insufficient Local VRAM? Ways to Run Kimi K3.1 Pro (2.8T MoE)

Rent an hourly high-VRAM cloud GPU pod, or check the 12-month Buy vs Cloud vs API break-even curve.

📊 Kimi K3.1 Pro (2.8T MoE) Quantization VRAM Breakdown (16K Context)

Quantization Bits/Weight Weights KV Cache (16K) Total VRAM Quality Note
FP16 / BF16 16 bpw 5560 GB 1.76 GB 5674.26 GB Lossless Full Precision
FP8 / Q8_0 8.5 bpw 2953.75 GB 1.76 GB 3015.88 GB 99.9% Near-Lossless
GGUF Q6_K 6.56 bpw 2279.6 GB 1.76 GB 2328.25 GB Ultra High Quality
GGUF Q5_K_M 5.69 bpw 1977.28 GB 1.76 GB 2019.88 GB High Balanced Quality
Q4_K_M / AWQ 4.85 bpw 1685.37 GB 1.76 GB 1722.14 GB Sweet Spot (Recommended)
GGUF IQ4_XS 4.25 bpw 1476.88 GB 1.76 GB 1509.47 GB Compact 4-bit
GGUF Q3_K_M 3.91 bpw 1358.73 GB 1.76 GB 1388.95 GB Moderate Perplexity Loss
GGUF Q2_K 3.15 bpw 1094.63 GB 1.76 GB 1119.57 GB Extreme Compression

🖥️ GPU & Apple Silicon Compatibility for Kimi K3.1 Pro (2.8T MoE) (Q4_K_M)

Frequently Asked Questions

What are the exact architecture parameters of Kimi K3.1 Pro (2.8T MoE)?

Kimi K3.1 Pro (2.8T MoE) uses KimiK31ForConditionalGeneration with 93 layers (93-Layer Sparse MoE (896 Experts, Top-50 Active)), hidden_size=7168, 96 Q heads / 96 KV heads (head_dim=75), and vocab_size=163,840.

How much VRAM does Kimi K3.1 Pro (2.8T MoE) require?

At 4-bit quantization (Q4_K_M, 16K context), Kimi K3.1 Pro (2.8T MoE) requires 1722.14 GB VRAM. Full FP16 requires 5674.26 GB.