Kimi K2 1T-A32B
Kimi K2 1T-A32B canonical official release.
Moonshot AIMixture of expertsagentic0 machines can run it
Total parameters
1.0T
Official spec sets memory need
Active parameters
32B
Official spec sets decode speed
Context
128K
Official spec tokens
4-bit weights
559 GB
Calculated before KV cache
This is a sparse mixture of experts. All 1.0T of weights must be available to the runtime, but only 32B are read per generated token. Ordinary runtimes keep the full quantized model in memory; a runtime-specific SSD-streaming artifact can retain a smaller working set and fetch expert data on demand, trading speed for capacity.
Model specification
Publisher
Moonshot AI Official spec
Architecture
Sparse mixture of experts Official spec
Total parameters
1.0T Official spec
Active parameters
32B per token Official spec
Context length
131,072 tokens Official spec
Attention ⓘ
MLA · 64 KV heads × 192 dim × 61 layers Official spec
Licence
Modified MIT Official spec
Specification confidence ⓘ
High · verified 2026-09-26 Official spec source
Released
11 Jul 2025 Official spec
Official source
Quantizations and memory
| Quantization | Format | Bits/weight | Resident | Download | Quality kept |
|---|---|---|---|---|---|
MLX 4-bit | mlx | 4.5 | 559.2 GB | 559.2 GB | 98.0% |
Q4_K_Mdefault | gguf | 4.85 | 596.9 GB | 596.9 GB | 98.5% |
Q5_K_M | gguf | 5.69 | 700.3 GB | 700.3 GB | 99.3% |
Q8_0 | gguf | 8.5 | 1036.0 GB | 1036.0 GB | 99.9% |
Generic weight sizes are computed from the parameter count and bits per weight plus a format-specific overhead. Runtime-specific artifacts use their published resident and download footprints; streamed models can therefore require much more disk than memory. Quality retention is an assumption, not a measured evaluation.
Coding & quality benchmarksCompare coding results →
No published benchmark results have been imported for this model yet. This is missing evidence, not a score of zero.
We show source metrics rather than deriving one opaque quality number. Different benchmarks measure genuinely different things, and collapsing them into a single score would hide exactly the disagreements worth seeing.
Recommendations
Cheapest that can run it
Nothing in the database qualifies.
Lowest purchase price among configurations where the model fits at some quantization in our catalogue. Speed is not considered.
Cheapest above 20 t/s
Nothing in the database qualifies.
20 tokens/second is roughly the point at which generation keeps pace with reading. Below it, interactive use feels like waiting.
Cheapest above 40 t/s
Nothing in the database qualifies.
40 tokens/second is the threshold most people describe as comfortable for coding agents, where output arrives faster than you can review it.
Fastest with real measurements
Nothing in the database qualifies.
Highest throughput among configurations with an actual published measurement rather than our estimate.
Best throughput per purchase-price unit
Nothing in the database qualifies.
Highest decode tokens/second per 1,000 units of the displayed purchase currency. Ignores running costs and resale — see the economics section for the full picture.
Hardware that runs Kimi K2 1T-A32B0 measured, 0 estimated
0 of 0 rows
| Hardware↕ | Quant | Memory↕ | Decode▼ | Prefill↕ | Context | Price↕ | Fit | Confidence↕ |
|---|---|---|---|---|---|---|---|---|
| Nothing matches these filters. | ||||||||
Similar models
Kimi K2.6
Moonshot AI · 1.0T (32B active) · Modified MIT
MiMo-V2.6 Pro 1.02T-A42B
XiaomiMiMo · 1.0T (42B active) · MIT
DeepSeek-V4.1 Flash
DeepSeek · 763.205B (16B active) · MIT
MiniMax M3
MiniMax · 427.04B (23B active) · Apache 2.0
MiMo-V2.6 Flash 309B-A15B
XiaomiMiMo · 309B (15B active) · MIT
Step 3.7 Flash 198B-A11B
StepFun · 201.365B (11B active) · Apache 2.0