Magnum v4 72B
Anthracite · released Sep 20, 2024 · anthracite-org/magnum-v4-72b
- Type
- Open weightsApache License 2.0
- Params
- 72.7B
- Context
- 16K
about 12K words of context
Our take
Written Sep 3, 2026Magnum v4 is a 72.7-billion-parameter text model from Anthracite with a permissive Apache licence for commercial use. Its context limit is modest at 16,384 tokens and no benchmark scores are available in our data.
Pick this when you need a permissive licence for commercial or derivative work and measured quality is not a blocker. Use it if you are budget-constrained and no cheaper 70-billion-parameter option is available. Skip it if you need a long context window, verified quality scores, or multimodal input.
The case for it
- Apache 2.0 licence allows unrestricted commercial use and fine-tuning.
- Identical pricing across both tracked providers, so provider choice comes down to features rather than cost.
The case against it
- No benchmark scores in our data — no verified chat, reasoning or coding quality.
- 16,384-token context window is narrow for its parameter class.
- Throughput unverified on one of two offers; the other lists 16 tokens per second.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M2 Max (38-core GPU) · 96 GB
Room to spare. 22.9 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $2.50 in / $5.00 out
- Context served
- 33K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.50 / $5.00checked 4 hours ago | 33K | not measured | Unknown | Unknown | Unknown |
| Mancer 2fp8Through OpenRouter | $2.50 / $5.00checked 4 hours ago | 33K4K max reply | 17 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✓ |
| Mancer 2fp8Through OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
input −17% ($3.00 → $2.50 per 1M tokens)What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- anthracite-org/magnum-v4-72b
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- anthracite-org-magnum-v4-72b