granite-guardian-3.3-8b
Model Summary: Granite Guardian 3.3 8b is a specialized Granite 3.3 8B model designed to judge if the input prompts and the output responses of an LLM based system meet specified criteria. The model comes pre-baked with certain criteria including but not limited to: jailbreak attempts, profanity, and hallucinations related to tool calls and retrieval augmented generation in agent-based systems. Additionally, the mode...
Params
8.2 B
Context
131,072
Downloads 30d
204 K
Likes
34
Download history
daily snapshots · 60 days
▲ 0 in the last 30 days (0.0%)
204 K204 K
Sep 26Oct 6Oct 16Oct 25
218 K204 K
Aug 27Sep 16Oct 6Oct 25
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 | 16.3 GB | 19.7 GB | ⚠️ Tight — reduce context |
| model.safetensors (bf16, full) | bf16 + 128K ctx | 16.3 GB | 38.1 GB | ❌ Won’t fit |
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-guardian-3-3-8b
{
"hf_id": "ibm-granite/granite-guardian-3.3-8b",
"params_b": 8.17,
"context_length": 131072,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 204311,
"vram_estimates": [
{ "quant": "bf16", "gb": 19.7 }
],
"updated_at": "2026-08-27T01:00:22Z"
}
Specifications
- Architecture
- GraniteForCausalLM
- Parameters
- 8.2 B
- Tensor type
- BF16
- Context length
- 131,072
- Vocabulary
- 49,159
- Layers / heads
- 40 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2025-06-03
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-27
Compare with any text-generation model