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 Aug 3, 2026Magnum v4 is a 72.7-billion-parameter text-only model from Anthracite, released in 2024 with a permissive Apache licence. Its narrow 16,384-token request limit and complete lack of measured quality data make it a licence-first choice rather than a capability-first one.
Pick this when permissive licensing matters more than proven performance, or for Apache-licensed deployment where you cannot accept a more restrictive terms. Use it for budget-constrained text generation if you do not need benchmark-backed quality assurance. Skip it if you need a long request limit, multimodal input, or any measured capability scores.
The case for it
- Apache License 2.0 allows commercial use, modification and redistribution without restriction.
- Identical pricing across both tracked providers, so provider choice comes down to features rather than cost.
The case against it
- No benchmark scores of any kind in our data, so there is no measured quality or capability information.
- 16,384-token request limit is narrow for a model of this size, with no comparison figure available.
- OpenRouter throughput is unverified in our data; only one provider reports a speed figure.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Magnum v4 72B — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $3.00 in / $5.00 out
- Context served
- 16K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $3.00 / $5.00 | 16K | not measured | Unknown | Unknown | Unknown |
| Mancer 2fp8 | $3.00 / $5.00 | 16K | 25 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✓ |
| Mancer 2fp8 | ✗ | ✓ | ✓ |
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
Dates behind this page
Prices last checked 7h ago
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 board we watch has turned up a score, 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 do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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
- Modality record
- text->text
- Catalogue slug
- anthracite-org-magnum-v4-72b