Llama-3.2-1B-Instruct vs Llama-3.2-1B-Instruct-FP8
Specs, VRAM requirements and download trends — updated 2 September 2026.
meta-llama · A · Open weights
Params
1.2 B
Context
—
30d
1.3 M
llama3.2 licence · conditional
RedHatAI · B · Open weights
Params
1.5 B
Context
131,072
30d
185 K
llama3.2 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Llama-3.2-1B-Instruct | Llama-3.2-1B-Instruct-FP8 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 1.2 B | 1.5 B |
| Architecture | LlamaForCausalLM | LlamaForCausalLM |
| Context length | 60,000 | 131,072 |
| Licence | llama3.2 | llama3.2 |
| Commercial use | Conditional | Conditional |
| Languages | 8 | 8 |
| Downloads 30d | 1,331,481 | 185,376 |
| Downloads all time | 109.8 M | 6.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-09-18 | 2024-09-26 |
| API input price / 1M tokens | $0.027 | not on OpenRouter |
| API output price / 1M tokens | $0.20 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.23 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | — | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 54,000 | not on OpenRouter |
| API providers | 1 | not on OpenRouter |
| Tool calling | No | not on OpenRouter |
| Reasoning mode | No | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Llama-3.2-1B-Instruct
$0.23
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
9.3 M185 K
Llama-3.2-1B-Instruct
Llama-3.2-1B-Instruct-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.2-1B-Instruct · fp16
3.4 GB / 24 GB
Llama-3.2-1B-Instruct-FP8 · fp16 @ 128K ctx
6.3 GB / 24 GB