Kimi-K2-Instruct
- Messages with name field are now supported. We’ve also moved the chat template to a standalone file for easier viewing. - We further modified our chat template to improve its robustness. The default system prompt has also been updated. - We have updated our tokenizer implementation. Now special tokens like [EOS] can be encoded to their token ids. - We fixed a bug in the chat template that was breaking multi-turn to...
Params
1,026.5 B
Context
131,072
Downloads 30d
277 K
Likes
3,010
Download history
daily snapshots · 106 days
▲ 60 K in the last 30 days (17.8%)
371 K277 K
Oct 12Oct 22Nov 1Nov 10
371 K162 K
Aug 13Sep 12Oct 12Nov 10
371 K162 K
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f8_e4m3 | 1,029.2 GB | 1,286.6 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 128K ctx | 1,029.2 GB | 3,596.1 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/kimi-k2-instruct
{
"hf_id": "moonshotai/Kimi-K2-Instruct",
"params_b": 1026.47,
"context_length": 131072,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 277334,
"vram_estimates": [
{ "quant": "f8_e4m3", "gb": 1286.6 }
],
"updated_at": "2026-07-28T18:08:36Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-11-10$0.57
input / 1M
$2.30
output / 1M
—
cached input / 1M
$2.87
1M in + 1M out
- Context window
- 131,072 tokens
- Max output
- 98,304 tokens
- Providers
- 1
- Cheapest provider
- Novita · $0.57 / $2.30
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✓ Tool calling
✗ Reasoning
✗ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✗ Prompt caching
Specifications
- Architecture
- DeepseekV3ForCausalLM
- Parameters
- 1,026.5 B
- Tensor type
- F8_E4M3
- Context length
- 131,072
- Vocabulary
- 163,840
- Layers / heads
- 61 / 64
- Licence
- other
- First seen on the Hub
- 2025-07-11
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-generation model