Anthracite ORG

Magnum v4 72B

Generally availableOpen weights33K context

Summary

Magnum v4 72B is an open-weight language model from Anthracite ORG, released on 22 Oct 2024. It accepts text and generates text, with a 33K-token context window and up to 4K output tokens per response. As of 19 Nov 2026, the lowest listed API price is $2.50 per million input tokens and $5 per million output tokens (OpenRouter), across 1 provider we track.

Open-weight instruction model for adaptable chat and self-hosted production workloads

Last verified 19 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperAnthracite ORG
Release date22 Oct 2024 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters72.7B [Hugging Face]
Context window33K (32,768 tokens) [models.dev]
Max output4K tokens [models.dev]
Knowledge cutoff30 Jun 2024 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]
Structured outputYes [models.dev]
Hugging Faceanthracite-org/magnum-v4-72b [Hugging Face]

Magnum v4 72B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
anthracite-org/magnum-v4-72b
$2.50$5$2.5033KOpenRouter, 19 Nov 2026

Running Magnum v4 72B locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)44 GB48 GB56 GB
Q8_0 (8-bit)77 GB81 GB89 GB
FP16 / BF16 (16-bit)145 GB149 GB157 GB

At 4-bit with an 8K conversation, Magnum v4 72B needs about 48 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of Magnum v4 72B?

Magnum v4 72B has a context window of 32,768 tokens (33K) and can generate up to 4,096 tokens in a single response, according to models.dev.

How much does the Magnum v4 72B API cost?

Magnum v4 72B is listed from $2.50 per million input tokens and $5 per million output tokens (OpenRouter). Prices last verified 19 Nov 2026.

Is Magnum v4 72B open source?

Magnum v4 72B is an open-weight model: its weights are published on Hugging Face as anthracite-org/magnum-v4-72b under the apache-2.0 license. Check the license terms before commercial use.

When was Magnum v4 72B released?

Anthracite ORG released Magnum v4 72B on 22 Oct 2024, according to models.dev.

How much VRAM does Magnum v4 72B need?

About 48 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 81 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Aion-RP 1.0 (8B)Aion Labs4 Feb 202533K$0.80$1.60Open
Mixtral 8x22B InstructMistral AI17 Apr 202466K$2$6Open
Mistral Large 2407Mistral AI24 Jul 2024128K$2$6Open
DeepSeek-R1DeepSeek20 Jan 202564K$0.70$2.50Open
Command R+Cohere30 Aug 2024128K$2.50$10Open
Skyfall 36B V2Thedrummer10 Mar 202533K$0.55$0.80Open

Change history

  • OpenRouter price changed: input $2.50 → $2.50, output $5 → $5 per 1M tokens

Sources