allenai / text-generation updated 7 months ago

Olmo-3-7B-Instruct-SFT

Name: Olmo-3-7B-Instruct-SFT
Author: allenai

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

306 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

353 K306 K

Jul 28Jul 31Aug 3Aug 6

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 · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/olmo-3-7b-instruct-sft
{
  "hf_id": "allenai/Olmo-3-7B-Instruct-SFT",
  "params_b": 7.30,
  "context_length": 65536,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 305992,
  "vram_estimates": [
    { "quant": "bf16", "gb": 17.7 }
  ],
  "updated_at": "2026-07-28T18:06:10Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

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: 2025-11-17
Training datasets: allenai/Dolci-Instruct-SFT, allenai/Dolci-Instruct-SFT-Tool-Use-SA
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB