SAVRN Model Hub · Comparisons
Prompt-Guard-86M vs xlm-roberta-base-language-detection
Prompt-Guard-86M has 279M parameters and xlm-roberta-base-language-detection has 278M parameters; Prompt-Guard-86M is released under Meta Llama 3.1 Community License and xlm-roberta-base-language-detection under MIT License; at 16-bit, Prompt-Guard-86M needs about 0.7 GB (1x MI300X from $1.85 an hour) and xlm-roberta-base-language-detection about 0.7 GB (1x MI300X from $1.85 an hour).
| Field | Prompt-Guard-86M meta-llama/Prompt-Guard-86M | xlm-roberta-base-language-detection papluca/xlm-roberta-base-language-detection |
|---|---|---|
| Publisher | Meta Llama | Luca Papariello |
| Task | Text classification | Text classification |
| Modality | Text | Text |
| Parameters, as reported | 279M parameters | 278M parameters |
| Architecture | DebertaV2ForSequenceClassification | XLMRobertaForSequenceClassification |
| Library | transformers | transformers |
| Context length | Not stated | 514 tokens |
| Repository size | 1.1 GB | 3.4 GB |
| Artifact formats | safetensors, pytorch | safetensors, pytorch, tf |
| License | llama3.1 | mit |
| Access | Access requested at publisher | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.7 GB | 0.7 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.2 GB | 0.2 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 1209add6ca7d | 9865598389ca |
| Downloads reported by the hub | 4.5M | 579k |
| Last observed | 2026-09-18 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on Prompt-Guard-86M
Nothing here generates a reply. It sits in front of the model that does and flags the two attack types Meta names, prompt injection and jailbreaks. Loaded at 16-bit it wants 0.7 GB of memory for 0.6 GB of weights, under half a percent of the cheapest Index setup, a single MI300X with 192 GB at $1.85 an hour on-demand. Co-locate it with the model it protects and the memory is noise.
Read the license closely. The Llama 3.1 Community License allows commercial use, but a licensee whose products had more than 700 million monthly active users on the release date must request a license from Meta, attribution is required, and Meta's Acceptable Use Policy applies. Access is gated; plan for the wait. The name says 86M while the file counts 279 million parameters, and no evaluations are reported, so you measure it on your own traffic before trusting it.
SAVRN's Notes on xlm-roberta-base-language-detection
Sorting inbound text by language before it reaches a larger model is the job this one does, with a 278M-parameter XLM-RoBERTa classifier covering 20 languages. At 16-bit the weights take 0.6 GB and the run needs 0.7 GB; at 8-bit it fits in 0.3 GB. It never gets its own accelerator in our facilities. It rides beside whatever else is on the card, and the cheapest Index host, one MI300X with 192 GB at $1.85 per hour, would give it a fraction of one percent of its memory.
MIT is the license, so a commercial deployment only has to carry the copyright and permission notices. Two checks: the context window is 514 tokens, so long documents get chunked first, and the model is a fine-tune of FacebookAI/xlm-roberta-base on the papluca/language-identification dataset, worth reading if your traffic includes languages outside those 20.
Questions
Which is larger, Prompt-Guard-86M or xlm-roberta-base-language-detection?
Prompt-Guard-86M (279M parameters) is larger than xlm-roberta-base-language-detection (278M parameters), by the parameter counts their publishers report.
Which is cheaper to run, Prompt-Guard-86M or xlm-roberta-base-language-detection?
At 4-bit, Prompt-Guard-86M fits on 1x MI300X from $1.85 an hour and xlm-roberta-base-language-detection on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Prompt-Guard-86M commercially?
Yes, with conditions. Prompt-Guard-86M is released under Meta Llama 3.1 Community License. The Llama 3.1 Community License permits commercial use, except that a licensee whose products had more than 700 million monthly active users on the release date must request a license from Meta. It requires attribution as the license specifies and compliance with Meta's Acceptable Use Policy.
Can I use xlm-roberta-base-language-detection commercially?
Yes. xlm-roberta-base-language-detection is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.