granite-4.0-h-micro
📣 Update [10-07-2025]: Added a default system prompt to the chat template to guide the model towards more professional, accurate, and safe responses.
Params
3.2 B
Context
131,072
Downloads 30d
9 K
Likes
147
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)9 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 | 6.4 GB | 8.0 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 128K ctx | 6.4 GB | 15.2 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-4-0-h-micro
{
"hf_id": "ibm-granite/granite-4.0-h-micro",
"params_b": 3.19,
"context_length": 131072,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 9011,
"vram_estimates": [
{ "quant": "bf16", "gb": 8.0 }
],
"updated_at": "2026-10-19T06:00:26Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.017
input / 1M
$0.11
output / 1M
—
cached input / 1M
$0.13
1M in + 1M out
- Context window
- 131,000 tokens
- Max output
- 117,900 tokens
- Providers
- 1
- Cheapest provider
- Cloudflare · $0.017 / $0.11
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 5.1 / — / —
✗ Tool calling
✗ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✗ Prompt caching
Specifications
- Architecture
- GraniteMoeHybridForCausalLM
- Parameters
- 3.2 B
- Tensor type
- BF16
- Context length
- 131,072
- Vocabulary
- 100,352
- Layers / heads
- 40 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2025-09-16
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model