MODEL PROFILE

Magnum v4 72B

anthracite-org · magnum-v4-72b

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of Qwen2.5 72B.

Text generationstructured_outputs
Context window32,768 Token
Input → OutputText → Text
Model weightsOpen weights
Profile updated2026/11/10 12:42:08
OVERVIEW

Model overview

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of Qwen2.5 72B.

The summary below is compiled from sources by an AI model, not our own testing. Verify selection decisions against original sources and your workload.

Key features

  • Fine-tuned on Qwen2.5 72B to emulate the prose quality of Claude 3 Sonnet and Opus
  • Supports structured outputs via prompt-based or schema-guided generation
  • Large context window of 32,768 tokens

Limitations & considerations

  • No official benchmark scores, speed, or resource consumption metrics provided in source materials
  • License (Apache-2.0) permits use but does not imply commercial endorsement or warranty
  • No information available about multilingual capability, safety alignment, or instruction-following robustness
PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
OpenRouter · anthracite-org/magnum-v4-72b ↗USD 2.5USD 5Per million tokens2026/11/2 06:25:30

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

What base model is Magnum v4 72B built upon?

It is fine-tuned on Qwen2.5 72B.

Which Claude 3 models is Magnum v4 72B designed to emulate?

It is designed to replicate the prose quality of Claude 3 Sonnet and Claude 3 Opus.

Where can I find the official model repositories?

Official repositories are hosted on OpenRouter (https://openrouter.ai/anthracite-org/magnum-v4-72b) and Hugging Face (https://huggingface.co/anthracite-org/magnum-v4-72b).

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。