SAVRN Model Hub · Comparisons
all-distilroberta-v1 vs e5-base-v2
All-distilroberta-v1 has 82M parameters and e5-base-v2 has 109M parameters; all-distilroberta-v1 is released under Apache License 2.0 and e5-base-v2 under MIT License; at 16-bit, all-distilroberta-v1 needs about 0.2 GB (1x MI300X from $1.85 an hour) and e5-base-v2 about 0.3 GB (1x MI300X from $1.85 an hour).
| Field | all-distilroberta-v1 sentence-transformers/all-distilroberta-v1 | e5-base-v2 intfloat/e5-base-v2 |
|---|---|---|
| Publisher | Sentence Transformers | Liang Wang |
| Task | Sentence similarity | Sentence similarity |
| Modality | Text | Text |
| Parameters, as reported | 82M parameters | 109M parameters |
| Architecture | RobertaForMaskedLM | BertModel |
| Library | sentence-transformers | sentence-transformers |
| Context length | 514 tokens | 512 tokens |
| Repository size | 3.2 GB | 2.2 GB |
| Artifact formats | safetensors, onnx, openvino, pytorch, rust | safetensors, onnx, openvino, pytorch |
| License | apache-2.0 | mit |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.2 GB | 0.3 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0 GB | 0.1 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 842eaed40bee | f52bf8ec8c71 |
| Downloads reported by the hub | 2.8M | 890.2k |
| Last observed | 2026-10-16 | 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.
Other Reported Results
These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it.
e5-base-v2
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 77.7761 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric apComparison conditions not established | 42.0527 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 72.1204 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric accuracyComparison conditions not established | 92.8101 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric apComparison conditions not established | 89.4214 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric f1Comparison conditions not established | 92.8039 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 46.712 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 46.1154 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1Comparison conditions not established | 23.186 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_10Comparison conditions not established | 36.633 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_100Comparison conditions not established | 37.842 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1000Comparison conditions not established | 37.865 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_3Comparison conditions not established | 32.278 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_5Comparison conditions not established | 34.761 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1Comparison conditions not established | 23.4 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_10Comparison conditions not established | 36.721 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_100Comparison conditions not established | 37.937 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1000Comparison conditions not established | 37.96 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_3Comparison conditions not established | 32.302 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_5Comparison conditions not established | 34.894 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1Comparison conditions not established | 23.186 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_10Comparison conditions not established | 44.49 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_100Comparison conditions not established | 50.065 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1000Comparison conditions not established | 50.63 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_3Comparison conditions not established | 35.461 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_5Comparison conditions not established | 39.969 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1Comparison conditions not established | 23.186 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_10Comparison conditions not established | 6.97 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_100Comparison conditions not established | 0.951 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1000Comparison conditions not established | 0.099 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_3Comparison conditions not established | 14.912 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_5Comparison conditions not established | 11.152 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1Comparison conditions not established | 23.186 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_10Comparison conditions not established | 69.701 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_100Comparison conditions not established | 95.092 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1000Comparison conditions not established | 99.431 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_3Comparison conditions not established | 44.737 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_5Comparison conditions not established | 55.761 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArxivClusteringP2P | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 46.1031 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArxivClusteringS2S | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 39.6728 | intfloat Publisher reported |
Evaluated revision not stated | — |
SAVRN's Notes on all-distilroberta-v1
How much GPU does an 82M-parameter embedding model need? Almost none: 0.2 GB of weights at 16-bit, 0.1 GB at 8-bit, and the cheapest setup on our Index is one MI300X with 192 GB at $1.85 an hour, a card this model leaves nearly empty, so share it with other work. What you get is a 768-dimensional vector for each sentence or paragraph, meant for semantic search and clustering, inside a 514-token context, so anything longer gets chunked first.
Eight training sets are on record, among them s2orc, ms_marco, code_search_net, stackexchange_xml and eli5; ask whether your corpus looks like them. Apache 2.0 means shipping it inside a commercial product, modifying it and redistributing it are allowed once the license and notices are kept and changes stated. Download only the format you need: the 3.19 GB across 30 files spans safetensors, onnx, openvino, pytorch and rust, and one is enough.
SAVRN's Notes on e5-base-v2
Every passage this embedding model sees is capped at 512 tokens, so chunking comes before hardware. Liang Wang published it as a 109 million parameter BertModel with 12 layers and a 768-wide embedding, built for sentence similarity; it runs in 0.3 GB of memory at 16-bit and 0.1 GB at 8-bit. The cheapest setup on our Index is one MI300X with 192 GB at $1.85 per hour, so the card is bought for throughput, not weights. The 2.19 GB download across 24 files carries four formats, safetensors, ONNX, OpenVINO and PyTorch, so load one.
MIT terms allow commercial use, modification and redistribution with the notices kept, so an index built on it can ship inside a product. Note that the benchmark results in the file are publisher reported, such as 92.81 accuracy on MTEB AmazonPolarityClassification, and the method sits in arXiv:2212.03533; test retrieval on your own corpus.
Questions
Which is larger, all-distilroberta-v1 or e5-base-v2?
e5-base-v2 (109M parameters) is larger than all-distilroberta-v1 (82M parameters), by the parameter counts their publishers report.
Which is cheaper to run, all-distilroberta-v1 or e5-base-v2?
At 4-bit, all-distilroberta-v1 fits on 1x MI300X from $1.85 an hour and e5-base-v2 on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use all-distilroberta-v1 commercially?
Yes. all-distilroberta-v1 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Can I use e5-base-v2 commercially?
Yes. e5-base-v2 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.