Llama-3.1-405B-FP8 vs GLM-5.3
Specs, VRAM requirements and download trends — updated 10 November 2026.
meta-llama · A · Open weights
Params
405.9 B
Context
—
30d
465 K
llama3.1 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Llama-3.1-405B-FP8 | GLM-5.3 |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 405.9 B | 753.3 B |
| Architecture | LlamaForCausalLM | GlmMoeDsaForCausalLM |
| Context length | — | 1,048,576 |
| Licence | llama3.1 | other |
| Commercial use | Conditional | Unknown |
| Languages | 8 | 2 |
| Downloads 30d | 465,185 | 2,016,722 |
| Downloads all time | 2.7 M | 4.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-07-20 | 2026-08-25 |
| API input price / 1M tokens | not on OpenRouter | $0.07 |
| API output price / 1M tokens | not on OpenRouter | $1.40 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $1.47 |
| Cached input / 1M tokens | not on OpenRouter | $0.069 |
| AA Intelligence Index | not on OpenRouter | 31.7 |
| AA Coding Index | not on OpenRouter | 74.8 |
| AA Agentic Index | not on OpenRouter | 53.1 |
| Max output tokens | not on OpenRouter | 943,718 |
| API providers | not on OpenRouter | 36 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5.3
$1.47
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.5 M304 K
Llama-3.1-405B-FP8
GLM-5.3
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.1-405B-FP8 · fp16
597.3 GB / 24 GB
GLM-5.3 · fp16 @ 1024K ctx
15,295.6 GB / 24 GB