Open-weight model
flaird-modernbert-large-attention-single-task
by Mahmood Anaam MahmoodAnaam/flaird-modernbert-large-attention-single-task
flaird-modernbert-large-attention-single-task is an open-weight model from Mahmood Anaam. It has 402M parameters. At 16-bit it needs about 1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 23 downloads a month.
Runs On
What it takes to serve flaird-modernbert-large-attention-single-task (402M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.8 GB | 1.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.4 GB | 0.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 19, 2026.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- FlairdForSequenceClassification
- Model type
- flaird
Identity and Version
- Repository
- MahmoodAnaam/flaird-modernbert-large-attention-single-task
- Publisher
- Mahmood Anaam
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 402M parameters
- Languages
- Not stated by the source
- Revision
- 80db2b1c1df5cbde8f93a6c0ad9c6d14c9921aa9
- First published
- 2026-09-17
- Last updated
- 2026-09-18
Files and Weights
20 files, 6.4 GB in total. The weights are 7 files totalling 6.4 GB in bin, pt, pth, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| last-checkpoint/model.safetensors | Weights | 1.6 GB | 62289657a434 |
| last-checkpoint/optimizer.pt | Weights | 3.2 GB | d006829786cc |
| last-checkpoint/rng_state.pth | Weights | 14.7 KB | 1f8ef8525ea0 |
| last-checkpoint/scheduler.pt | Weights | 1.5 KB | 3496398049dc |
| last-checkpoint/training_args.bin | Weights | 5.5 KB | 9d4ad97f7c5b |
| model.safetensors | Weights | 1.6 GB | 62289657a434 |
| training_args.bin | Weights | 5.5 KB | 9d4ad97f7c5b |
| config.json | Configuration | 4.6 KB | — |
| last-checkpoint/config.json | Configuration | 4.6 KB | — |
| last-checkpoint/configuration_flaird.py | Configuration | 4.9 KB | — |
| last-checkpoint/features.py | Configuration | 5.5 KB | — |
| last-checkpoint/modeling_flaird.py | Configuration | 9.7 KB | — |
| last-checkpoint/modeling_fusion.py | Configuration | 4.2 KB | — |
| last-checkpoint/trainer_state.json | Configuration | 38.5 KB | — |
| runs/Sep17_21-26-50_2485aac1ec50/events.out.tfevents.1789680410.2485aac1ec50.12972.0 | Other | 51.5 KB | ab53a67c5cab |
| .gitattributes | Repository | 1.5 KB | — |
| last-checkpoint/tokenizer.json | Tokenizer | 3.6 MB | — |
| last-checkpoint/tokenizer_config.json | Tokenizer | 380 B | — |
| tokenizer.json | Tokenizer | 3.6 MB | — |
| tokenizer_config.json | Tokenizer | 380 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 6.4 GB
Released by Mahmood Anaam through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.4 GB |
| 16-bit | 0.8 GB |
| 8-bit | 0.4 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About flaird-modernbert-large-attention-single-task
How much GPU memory does flaird-modernbert-large-attention-single-task need?
About 1 GB at 16-bit and 0.2 GB at 4-bit: the weights (402M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run flaird-modernbert-large-attention-single-task on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.