granite-4.1-8b vs Qwen3-14B
Specs, VRAM requirements and download trends — updated 25 August 2026.
ibm-granite · A · Open weights
Params
8.8 B
Context
131,072
30d
192 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | granite-4.1-8b | Qwen3-14B |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 8.8 B | 14.8 B |
| Architecture | GraniteForCausalLM | Qwen3ForCausalLM |
| Context length | 131,072 | 40,960 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 192,200 | 10,001,942 |
| Downloads all time | 6.1 M | 38.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-06 | 2025-04-27 |
| API input price / 1M tokens | not on OpenRouter | $0.12 |
| API output price / 1M tokens | not on OpenRouter | $0.24 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.36 |
| Cached input / 1M tokens | not on OpenRouter | — |
| AA Intelligence Index | not on OpenRouter | 6.7 |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 16,384 |
| API providers | not on OpenRouter | 2 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-14B
$0.36
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
10.0 M192 K
granite-4.1-8b
Qwen3-14B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-14B · fp16
35.2 GB / 24 GB
granite-4.1-8b · fp16 @ 128K ctx
40.9 GB / 24 GB