Olmo-3-7B-Instruct
We introduce Olmo 3, a new family of 7B and 32B models both Instruct and Think variants. Long chain-of-thought thinking improves reasoning tasks like math and coding.
Params
7.3 B
Context
65,536
Downloads 30d
276 K
Likes
146
Download history
daily snapshots · 55 days
▲ 214 K in the last 30 days (43.6%)
485 K224 K
Aug 22Sep 1Sep 11Sep 20
494 K224 K
Jul 28Aug 15Sep 2Sep 20
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 | 14.6 GB | 17.7 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 64K ctx | 14.6 GB | 25.3 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/olmo-3-7b-instruct
{
"hf_id": "allenai/Olmo-3-7B-Instruct",
"params_b": 7.30,
"context_length": 65536,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 276026,
"vram_estimates": [
{ "quant": "bf16", "gb": 17.7 }
],
"updated_at": "2026-07-28T18:06:56Z"
}
Specifications
- Architecture
- Olmo3ForCausalLM
- Parameters
- 7.3 B
- Tensor type
- BF16
- Context length
- 65,536
- Vocabulary
- 100,278
- Layers / heads
- 32 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2025-11-19
- Training datasets
- allenai/Dolci-Instruct-RL-7B
- Added to our catalog
- 2026-07-28
Compare with any text-generation model
Popular comparisons
Appears in