gemma-3-4b-it
Params
4.3 B
Context
—
Downloads 30d
1.0 M
Likes
1,640
Download history
daily snapshots · 106 days
▲ 189 K in the last 30 days (15.8%)
1.2 M950 K
Oct 12Oct 22Nov 1Nov 10
1.8 M950 K
Aug 13Sep 12Oct 12Nov 10
2.1 M950 K
Jul 28Sep 1Oct 6Nov 10
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 | 8.6 GB | 10.6 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-11-10$0.05
input / 1M
$0.10
output / 1M
—
cached input / 1M
$0.15
1M in + 1M out
- Context window
- 131,072 tokens
- Max output
- 16,384 tokens
- Providers
- 2
- Cheapest provider
- Parasail · $0.04 / $0.05
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / 2.7 / —
✗ Tool calling
✗ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✗ Prompt caching
Specifications
- Architecture
- Gemma3ForConditionalGeneration
- Parameters
- 4.3 B
- Tensor type
- BF16
- Licence
- gemma
- First seen on the Hub
- 2025-02-20
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any image-text-to-text model
Popular comparisons
Appears in