Llama-3.1-8B-Instruct vs granite-4.2-8b
Specs, VRAM requirements and download trends — updated 24 October 2026.
meta-llama · A · Open weights
Params
8.0 B
Context
—
30d
4.9 M
llama3.1 licence · conditional
ibm-granite · B · Open weights
Params
8.8 B
Context
131,072
30d
80 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Llama-3.1-8B-Instruct | granite-4.2-8b |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 8.0 B | 8.8 B |
| Architecture | LlamaForCausalLM | GraniteForCausalLM |
| Context length | 131,072 | 131,072 |
| Licence | llama3.1 | apache-2.0 |
| Commercial use | Conditional | Allowed |
| Languages | 8 | 12 |
| Downloads 30d | 4,864,172 | 80,469 |
| Downloads all time | 191.0 M | 192 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-07-18 | 2026-08-07 |
| API input price / 1M tokens | $0.05 | $0.06 |
| API output price / 1M tokens | $0.08 | $0.25 |
| Est. cost per 1M input + 1M output tokens | $0.13 | $0.31 |
| Cached input / 1M tokens | $0.025 | $0.015 |
| AA Intelligence Index | 6.9 | 11.1 |
| AA Coding Index | 5.4 | 22.4 |
| AA Agentic Index | — | 1.3 |
| Max output tokens | 117,964 | 117,964 |
| API providers | 5 | 2 |
| Tool calling | Yes | Yes |
| Reasoning mode | No | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Llama-3.1-8B-Instruct
$0.13
granite-4.2-8b
$0.31
Llama-3.1-8B-Instruct is 2.4× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
8.0 M86 K
Llama-3.1-8B-Instruct
granite-4.2-8b
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.1-8B-Instruct · fp16
19.4 GB / 24 GB
granite-4.2-8b · fp16 @ 128K ctx
40.9 GB / 24 GB