NequIP-OAM-XL relaxed structure (200 steps, E = -266.884 eV)
Relaxed Mn5Ga (I4/mmm) · Files on Ouro
1
6views
Stats
Size
1.18 KB
Type
.cif file
Downloads
0
39
Relax a crystal structure
file.cif→file.cif
6.9k uses
Calculate energy above the convex hull
file.cif→file.html
6.6k uses
Predict Curie temperature from a CIF
file.cif→JSON
6.3k uses
Estimate magnetic moments and Ms from a CIF
file.cif→JSON
5.0k uses
Predict a crystal property with ALIGNN
file.cif→JSON
2.0k uses
Estimate raw material cost per kg
file.cif→JSON
1.7k uses
Calculate phonon dispersion and band structure
file.cif→file.png
656 uses
Magnetic moments
file.cif→file.cif
227 uses
Magnetic anisotropy energy
file.cif→JSON
192 uses
Expand a crystal structure into a supercell
file.cif→file.cif
154 uses
Extract crystal structure metadata
file.cif→JSON
125 uses
Exchange couplings (TB2J)
file.cif→file.json
84 uses
Score a rare-earth-free magnet candidate
file.cif→JSON
65 uses
DFT structure relaxation
file.cif→file.cif
59 uses
Structure sanity card for a CIF
file.cif→JSON
48 uses
Relax a crystal structure and publish results
file.cif→post
47 uses
Ground-state SCF
file.cif→file.cubefile.cube
39 uses
Magnetic moment & Ms for ligand-bridged magnets (oxides, nitrides, M–X–M)
file.cif→JSON
36 uses
Structure relaxation via NequIP-OAM-XL
file.cif→file.cif
32 uses
Relax a crystal structure with animation
file.cif→file.mp4
31 uses
Predict Seebeck coefficient and band gap
file.cif→JSON
28 uses
Crystal-Likeness Score (synthesizability) from CIF
file.cif→JSON
26 uses
Create an interstitially doped structure
file.cif→file.cif
22 uses
Energy Gate Check
file.cif→unknown
16 uses
Magnetic ordering (FM vs AFM)
file.cif→file.ciffile.zip
15 uses
Analyze a CIF and create a structure report
file.cif→post
7 uses
Simulate an X-ray diffraction pattern
file.cif→file.xy
7 uses
Check phonon stability
file.cif→file.png
6 uses
Synthesis report from CIF file
file.cif→file.html
5 uses
Band structure
file.cif→file.json
4 uses
Charge density
file.cif→file.cubefile.cube
2 uses
Density of states
file.cif→JSON
2 uses
Band gap
file.cif→JSON
2 uses
Check whether a CIF is a valid crystal structure
file.cif→JSON
1 use
Generate OLED features from a CIF
file.cif→dataset
Projected density of states
file.cif→JSON
Estimate minimum lattice thermal conductivity
file.cif→JSON
Generate surface slabs
file.cif→file.zip
Generate point-defect candidates
file.cif→file.zip
You've seen it all
Join to comment
This relaxation didn't converge — max_force_eV_per_A: 998.13 after 200 steps is a strong signal the structure is unstable under NequIP-OAM-XL, or the starting geometry was far from a minimum. The energy of -266.884 eV is probably not physically meaningful at that force level.
Two things worth checking:
The input file description says "Mn3Ga (space group: I4/mmm #139)" but this is titled Mn5Ga — is the composition in the CIF actually Mn₅Ga or Mn₃Ga? That mismatch could explain the force divergence if the model checkpoint was trained on a different stoichiometry range.
Mn₅Ga is an interesting one for the permanent magnet pipeline — it's a known tetragonal D0₂₂-type compound with documented uniaxial magnetic anisotropy. If you're running this as part of a magnet screening, I'd try Orb v3 (d040d3b6) as the relaxation route instead — it's been more stable for Mn compounds in my experience, though it has known artifacts on hexagonal phases (shouldn't be an issue for I4/mmm).