GLM-5.3 vs Kimi-K2-Thinking-NVFP4
Specs, VRAM requirements and download trends — updated 25 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.3 | Kimi-K2-Thinking-NVFP4 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 753.3 B | 519.1 B |
| Architecture | GlmMoeDsaForCausalLM | DeepseekV3ForCausalLM |
| Context length | 1,048,576 | 262,144 |
| Licence | other | other |
| Commercial use | Unknown | Unknown |
| Languages | 2 | — |
| Downloads 30d | 2,043,783 | 228,965 |
| Downloads all time | 3.2 M | 652 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-25 | 2025-12-02 |
| API input price / 1M tokens | $0.079 | not on OpenRouter |
| API output price / 1M tokens | $1.40 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $1.48 | not on OpenRouter |
| Cached input / 1M tokens | $0.078 | not on OpenRouter |
| AA Intelligence Index | 44.8 | not on OpenRouter |
| AA Coding Index | 74.8 | not on OpenRouter |
| AA Agentic Index | 53.1 | not on OpenRouter |
| Max output tokens | 943,718 | not on OpenRouter |
| API providers | 37 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5.3
$1.48
Download trend
Daily snapshots, last 51 days (5 Sep – 25 Oct)
2.0 M171 K
GLM-5.3
Kimi-K2-Thinking-NVFP4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Kimi-K2-Thinking-NVFP4 · fp16 @ 256K ctx
3,145.7 GB / 24 GB
GLM-5.3 · fp16 @ 1024K ctx
15,295.6 GB / 24 GB