anthracite-org
Magnum v4 72B
anthracite-org/magnum-v4-72b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
anthracite-org/magnum-v4-72b is a 72B-parameter text-to-text model documented as a full-parameter fine-tune of Qwen2.5-72B-Instruct. Its stated goal is to approximate the prose quality associated with Claude 3 Sonnet and Opus, but the supplied evidence does not include measurements proving that result. The OpenRouter catalog lists a 32,768-token context window, text-only input and output, and broad generation controls. The model card calls the training approach experimental and provides ChatML-style prompting plus SillyTavern templates, indicating a conversational writing orientation.[1][2]
Strengths
- Full-parameter fine-tune of Qwen2.5-72B-Instruct, rather than an adapter, according to the model card.[2]
- Author-documented ChatML prompting and SillyTavern templates support conversational and persona-driven use.[2]
- Catalog lists a 32,768-token context and controls for structured outputs, sampling, penalties, and seeds.[1]
Limitations
Where to use it
- Possible fit for drafting or polishing prose where Claude-like style is desired, pending evaluation.[1][2]
- Possible fit for character dialogue or narrative roleplay, supported by the supplied SillyTavern templates.[2]
- Possible fit for text-only generation needing structured output or seed-controlled experiments within 32,768 tokens.[1]
Sources
- [1] OpenRouter catalog · Magnum v4 72BSources checked: Nov 13, 2026
- [2] Model documentation · Magnum v4 72BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).
Specifications
- Model ID
- anthracite-org/magnum-v4-72b
- Creator
- anthracite-org
- Added to OpenRouter
- 22.10.2024
- Context length
- 32,768
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $2.5 / out $5
- Knowledge cutoff
- 30.06.2024
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Mancer 2fp8 | 32,768 | $2.5 | $5 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.