granite-3.3-2b-instruct
Model Summary: Granite-3.3-2B-Instruct is a 2-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities. Built on top of Granite-3.3-2B-Base, the model delivers significant gains on benchmarks for measuring generic performance including AlpacaEval-2.0 and Arena-Hard, and improvements in mathematics, coding, and instruction following. It supports stru...
Params
2.5 B
Context
131,072
Downloads 30d
340 K
Likes
87
Download history
daily snapshots · 16 days344 K329 K
Oct 9Oct 14Oct 19Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 5.1 GB | 6.5 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 128K ctx | 5.1 GB | 12.2 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/granite-3-3-2b-instruct
{
"hf_id": "ibm-granite/granite-3.3-2b-instruct",
"params_b": 2.53,
"context_length": 131072,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 340490,
"vram_estimates": [
{ "quant": "bf16", "gb": 6.5 }
],
"updated_at": "2026-10-09T01:00:14Z"
}
Specifications
- Architecture
- GraniteForCausalLM
- Parameters
- 2.5 B
- Tensor type
- BF16
- Context length
- 131,072
- Vocabulary
- 49,159
- Layers / heads
- 40 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2025-04-09
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-09
Compare with any text-generation model