gpt-oss-120b vs magnum-v4-72b
Specs, VRAM requirements and download trends — updated 25 October 2026.
openai · A · Open weights
Params
120.4 B
Context
131,072
30d
2.9 M
apache-2.0 · commercial OK
anthracite-org · B · Open weights
Params
72.7 B
Context
32,768
30d
880
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt-oss-120b | magnum-v4-72b |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 120.4 B | 72.7 B |
| Architecture | GptOssForCausalLM | Qwen2ForCausalLM |
| Context length | 131,072 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 2,893,802 | 880 |
| Downloads all time | 60.5 M | 50 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-08-04 | 2024-09-20 |
| API input price / 1M tokens | $0.15 | $2.50 |
| API output price / 1M tokens | $0.60 | $5.00 |
| Est. cost per 1M input + 1M output tokens | $0.75 | $7.50 |
| Cached input / 1M tokens | $0.075 | — |
| AA Intelligence Index | 11.6 | — |
| AA Coding Index | 30.4 | — |
| AA Agentic Index | 3.7 | — |
| Max output tokens | 65,536 | 4,096 |
| API providers | 22 | 1 |
| Tool calling | Yes | No |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gpt-oss-120b
$0.75
magnum-v4-72b
$7.50
gpt-oss-120b is 10.0× cheaper at list price.
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
5.5 M800
gpt-oss-120b
magnum-v4-72b
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
magnum-v4-72b · fp16
171.4 GB / 24 GB
gpt-oss-120b · fp16 @ 128K ctx
433.0 GB / 24 GB