Kimi K2.7 Code (1T MoE) Architecture Parameters, Benchmarks & VRAM
1T total / 32B active coding & UI-to-code multimodal specialist from Moonshot AI.
🧬 Kimi K2.7 Code (1T MoE) Architecture & Tensor Specifications
Verified directly against HuggingFace (moonshotai/Kimi-K2.7-Code) config.json & Model Card
1. Backbone & Dimensions
kimi_k25- Total / Active Params
- 1.026T / 32B
- Hidden Size (d_model)
- 7,168
- FFN Intermediate Size
- 18,432
- MoE Expert Dim
- 2,048
- MoE Experts
- 384 Routed · Top-8 + 1 Shared
- Activation / Norm
- SiLU (SwiGLU) · ε=0.00001
- Native Tensor Dtype
- BF16 / FP8
2. Attention & Layer Layout
MLA- Num Hidden Layers
- 61 Layers
- Hidden Layer Layout
- 61-Layer Sparse MoE (384 Experts, Top-8 Active)
- Attention Heads (Q / KV)
- 64 Q / 64 KV
- Head Dimension
- 112
3. Context, RoPE & Tokenizer
Tokenizer- Native Context Length
- 262,144 tokens
- RoPE Configuration
- RoPE (原生 262,144 Context)
- Vocab Size
- 163,840 (Untied)
📋 Kimi K2.7 Code (1T MoE) Official API & System Card Specifications
Verified against official Moonshot Kimi developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- kimi-k2.7-code
- Release Date
- 2026-06-12
- 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
- 256,000 tokens (256K)
- Max Output Tokens
- 262,000 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
- ¥ 6.5
- Cached Input / 1M
- ¥ 1.3 -80%
- Output / 1M Tokens
- ¥ 27
- Tiered Pricing Notes
- Moonshot AI: Moonshot AI official CN platform with auto prefix cache
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Kimi K2.7 Code (1T MoE) Full Benchmark Scorecard
8 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 6 items
MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.
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…
Program Bench evaluates code-generation agents by asking them to recreate a program's behavior from only a compiled binary and documentation.
MLS-Bench Lite is the official 30-task subset of MLS-Bench for evaluating whether AI systems can invent generalizable and scalable machine learning methods across LLM pretraining and post-training, robotics, world models, computer vision, reinforcement learning, optimization, ML…
DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.
FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.
🤖 Agents & Tools 1 items
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
⚡ Kimi K2.7 Code (1T MoE) Interactive VRAM & Token Speed Calculator
Physical 96 GB · Load 677%
Exceeds usable VRAM by 542.82 GB
MLA compresses multi-batch KV footprint
OLLAMA_CONTEXT_LENGTH=16384 ollama run kimi-k2-7-code-1000bInsufficient Local VRAM? Ways to Run Kimi K2.7 Code (1T MoE)
Rent an hourly high-VRAM cloud GPU pod, or check the 12-month Buy vs Cloud vs API break-even curve.
📊 Kimi K2.7 Code (1T MoE) Quantization VRAM Breakdown (16K Context)
| Quantization | Bits/Weight | Weights | KV Cache (16K) | Total VRAM | Quality Note |
|---|---|---|---|---|---|
| FP16 / BF16 | 16 bpw | 2052 GB | 1.15 GB | 2095.49 GB | Lossless Full Precision |
| FP8 / Q8_0 | 8.5 bpw | 1090.13 GB | 1.15 GB | 1114.38 GB | 99.9% Near-Lossless |
| GGUF Q6_K | 6.56 bpw | 841.32 GB | 1.15 GB | 860.6 GB | Ultra High Quality |
| GGUF Q5_K_M | 5.69 bpw | 729.74 GB | 1.15 GB | 746.79 GB | High Balanced Quality |
| Q4_K_M / AWQ | 4.85 bpw | 622.01 GB | 1.15 GB | 636.9 GB | Sweet Spot (Recommended) |
| GGUF IQ4_XS | 4.25 bpw | 545.06 GB | 1.15 GB | 558.42 GB | Compact 4-bit |
| GGUF Q3_K_M | 3.91 bpw | 501.46 GB | 1.15 GB | 513.94 GB | Moderate Perplexity Loss |
| GGUF Q2_K | 3.15 bpw | 403.99 GB | 1.15 GB | 414.52 GB | Extreme Compression |
🖥️ GPU & Apple Silicon Compatibility for Kimi K2.7 Code (1T MoE) (Q4_K_M)
Frequently Asked Questions
What are the exact architecture parameters of Kimi K2.7 Code (1T MoE)?
Kimi K2.7 Code (1T MoE) uses KimiK25ForConditionalGeneration with 61 layers (61-Layer Sparse MoE (384 Experts, Top-8 Active)), hidden_size=7168, 64 Q heads / 64 KV heads (head_dim=112), and vocab_size=163,840.
How much VRAM does Kimi K2.7 Code (1T MoE) require?
At 4-bit quantization (Q4_K_M, 16K context), Kimi K2.7 Code (1T MoE) requires 636.9 GB VRAM. Full FP16 requires 2095.49 GB.