granite-4.2-8b
------ Developers Granite Team, IBM Model Type Decoder-only Dense Transformer (Reasoning) Architecture GraniteForCausalLM Base Model Granite-4.1-8B-Base Parameters 8B Context Length Natively Supports 128K (Long-context extension to 512K) Precision bfloat16 Tested Languages English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, Chinese (other languages may work but have not been...
Params
8.8 B
Context
131,072
Downloads 30d
80 K
Likes
107
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)80 K downloads in the last 30 days
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 | 17.6 GB | 21.2 GB | ⚠️ Tight — reduce context |
| model.safetensors (bf16, full) | bf16 + 128K ctx | 17.6 GB | 40.9 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-4-2-8b
{
"hf_id": "ibm-granite/granite-4.2-8b",
"params_b": 8.79,
"context_length": 131072,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 80469,
"vram_estimates": [
{ "quant": "bf16", "gb": 21.2 }
],
"updated_at": "2026-10-19T06:02:24Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.06
input / 1M
$0.25
output / 1M
$0.015
cached input / 1M
$0.31
1M in + 1M out
- Context window
- 131,072 tokens
- Max output
- 117,964 tokens
- Providers
- 2
- Cheapest provider
- DeepInfra · $0.06 / $0.25
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 11.1 / 22.4 / 1.3
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- GraniteForCausalLM
- Parameters
- 8.8 B
- Tensor type
- BF16
- Context length
- 131,072
- Vocabulary
- 100,352
- Layers / heads
- 40 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2026-08-07
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model