Models / Anthracite/ Magnum v4 72B

Magnum v4 72B

Anthracite · released Sep 20, 2024 · anthracite-org/magnum-v4-72b

Input: text. Output: text.InputOutput
Type
Open weightsApache License 2.0
Params
72.7B
Context
16K

about 12K words of context

Our take

Written Aug 3, 2026

Magnum 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.

Who should pick it

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.
00

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.

The boards we watch →

01

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%
A card many people ownToo large

GeForce RTX 4090 · 24 GB

Weights at Q4_K_M45.8 / 24 GBest
Usable contextNot calculated for spilled setups
Decode speedNot estimated for spilled setups

Too large for this card. The weights do not fit even with part of them offloaded to system memory.

One step upToo large

Apple M1 Pro (16-core GPU) · 32 GB

Weights at Q4_K_M45.8 / 32 GBest
Usable contextNot calculated for spilled setups
Decode speedNot estimated for spilled setups

Too large for this card. The weights do not fit even with part of them offloaded to system memory.

Comfortable fit

On a MacFits in memory

Apple M2 Max (38-core GPU) · 96 GB

Weights at Q4_K_M45.8 / 96 GBest
Spare memory22.9 GB spare
Usable context16K of 16K
Decode speed6 tok/sest

Room to spare. 22.9 GB spare means a 10% error in the size would not change the answer.

Your hardware
Checking your profile…

Memory use by level

Against a 24 GB card.

Q4_K_M
recommended
45.8 GBest
Too large
Q5_K_M
53.8 GBest
Too large
Q8_0
80.3 GBest
Too large

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 →

02

Or rent it from someone else

Cheapest published offer

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
Current provider offers with price, context and prompt-privacy answers
ProviderIn / out per 1M tokensContextThroughputTrains on promptsLogs promptsZero retention
OpenRouter$3.00 / $5.0016Knot measuredUnknownUnknownUnknown
Mancer 2fp8$3.00 / $5.0016K25 tok/sNoNoConfirmed

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
API features per host
ProviderTool callingJSON outputStrict 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.

03

When we formed this view

Dates behind this page

Jul 26, 2026ListedListed on LLMapfirst indexed by our pipeline
Sep 20, 2024AnnouncedMagnum v4 72B announced by Anthracite

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.
04

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

permissiveCommercial use allowed

Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.

Identifiers

Architecture
Dense
Modality record
text->text
Catalogue slug
anthracite-org-magnum-v4-72b

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us