The story so far
Weights, every dated article, and repo commits on one rail.
Most coverage came in the first two weeks
Teal is the weights (2024-04-11), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
Up to date
Snowflake Apache 2.0 out 3 years ago
109M parameters, text in, embeddings out, 512 tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #61 in Embeddings · score 86.2 method v1 Sources 3 Downloads 30d 375.7k · #189 of 619 tracked
Picked by rule from 32 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Wiz Red Agent discovered and exploited a script injection vulnerability in Snowflake's GitHub Actions workflow that GitHub Advanced Security missed.
The 2 picks above, plus these 23. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | HF Inference | — | — | — | — | Oct 25 |
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; 5 quantized builds for local use; a big base for builders (53 fine-tunes, adapters and merges).
Top Spaces running it: HuggingFaceFW/blogpost-fineweb-v1 ♥ 1,455 · nsarrazin/rag-tool-template ♥ 10 · huggingchat/document-parser-rag ♥ 8 · Ki-Seki/blogpost-fineweb-v1 ♥ 7
Weights only, an estimate: leave room for the KV cache. Method
About 0.1 GB at INT4, 0.1 GB at FP8, 0.3 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Third-party measurements only; author-reported numbers stay in Reference, marked as such.
61.09. Each tick is a model on this site with a measured MTEB row; author-reported numbers stay in Reference. Mean(task) x100 over 41 tasks. 41 tasks, split=test
Source · leaderboard · 2026-10-24
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2024-04-11), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
58 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| measured MTEB · Embed text for search | 57.53 nDCG@10 x100 (mean of 10 tasks) | 10 tasks, split=test | leaderboard | 2026-10-24 |
| measured MTEB · Embed text for search | 61.09 mean(task) x100 over 41 tasks | 41 tasks, split=test | leaderboard | 2026-10-24 |
| measured MTEB Reranking · Rerank search results | 44.85 MAP x100 (mean of 2 tasks) | 2 tasks, split=test | leaderboard | 2026-10-24 |
| author-reported MTEB · Embed text for search | 54.9 | snowflake-arctic-embed-m | model author | 2026-10-07 |
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in Embeddings
| Pipeline tag | sentence-similarity |
|---|---|
| Library | sentence-transformers |
| Architectures | BertModel |
| Model type | bert |
| Dtype | float32 |
| Params by dtype | F32: 108,891,648 |
| Size band | S |
| MoE | no |
| Context length | 512 (config.json max_position_embeddings) |
| Papers | arXiv:2407.18887, arXiv:2405.05374 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · BertModel · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · BertModel · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for snowflake-arctic-embed-m: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.3 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 0.1 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.1 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 5finetune: 53
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| mlc-ai/snowflake-arctic-embed-m-q0f32-MLC | quantized | — | — | — | — | mlc-ai | 2 | 15.2k |
| HuggingFaceTB/python-edu-scorer | finetune | — | 109M | S | apache-2.0 | HuggingFaceTB | 31 | 3.7k |
| mradermacher/snowflake-arctic-embed-m-i1-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 1 | 4.8k |
| mradermacher/snowflake-arctic-embed-m-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 1 | 2.2k |
| Torekhan/sentence_similarity_model | finetune | — | 109M | S | — | Torekhan | 0 | 1.3k |
| cstr/snowflake-arctic-embed-m-GGUF | quantized | GGUF | — | — | apache-2.0 | cstr | 0 | 1k |
| zenml/finetuned-snowflake-arctic-embed-m | finetune | — | 109M | S | apache-2.0 | zenml | 1 | 584 |
| khoj-ai/timely-arctic-medium | finetune | — | 109M | S | — | khoj-ai | 0 | 593 |
| Mr-Cool/midterm-finetuned-embedding | finetune | — | 109M | S | — | Mr-Cool | 0 | 486 |
| Vira21/finetuned_arctic | finetune | — | 109M | S | — | Vira21 | 0 | 479 |
| ve88ifz2/snowflake-arctic-embed-m-klej-dyk-v0.1 | finetune | — | 109M | S | apache-2.0 | ve88ifz2 | 0 | 474 |
| bsmith3715/legal-ft-demo_final | finetune | — | 109M | S | — | bsmith3715 | 0 | 454 |
| llm-wizard/legal-ft-v0-midterm | finetune | — | 109M | S | — | llm-wizard | 0 | 425 |
| llm-wizard/state-of-ai-embeddings | finetune | — | 109M | S | — | llm-wizard | 0 | 421 |
| rchrdgwr/finetuned-arctic-model-2 | finetune | — | 109M | S | — | rchrdgwr | 0 | 403 |
| drewgenai/demo-compare-arctic-embed-m-ft | finetune | — | 109M | S | — | drewgenai | 0 | 390 |
| drewgenai/finetuned_arctic_ft | finetune | — | 109M | S | — | drewgenai | 0 | 342 |
| XicoC/midterm-finetuned-arctic | finetune | — | 109M | S | — | XicoC | 0 | 340 |
| JoeNoss1998/Noss | finetune | — | 109M | S | — | JoeNoss1998 | 0 | 332 |
| ldldld/snowflake-arctic-embed-m-finetuned | finetune | — | 109M | S | — | ldldld | 0 | 327 |
| northstaranlyticsma24/artic_ft_midterm | finetune | — | 109M | S | — | northstaranlyticsma24 | 0 | 321 |
| JoeNoss1998/Niss | finetune | — | 109M | S | — | JoeNoss1998 | 0 | 309 |
| Cheselle/finetuned-arctic-sentence | finetune | — | 109M | S | — | Cheselle | 0 | 305 |
| achapman/finetuned_arctic_ai_risk | finetune | — | 109M | S | — | achapman | 0 | 301 |
| jet-taekyo/snowflake_finetuned_recursive | finetune | — | 109M | S | — | jet-taekyo | 0 | 300 |
| vijayarulmuthu/finetuned_arctic_ft-a85433c9-6284-4afb-8e87-e110823d565c | finetune | — | 109M | S | — | vijayarulmuthu | 0 | 289 |
| rgtlai/ai-policy-ft | finetune | — | 109M | S | — | rgtlai | 0 | 284 |
| bsmith3715/legal-ft-cert-challenge | finetune | — | 109M | S | — | bsmith3715 | 0 | 284 |
| niting089/finetuned_arctic | finetune | — | 109M | S | — | niting089 | 0 | 282 |
| drewgenai/midterm-compare-arctic-embed-m-ft | finetune | — | 109M | S | — | drewgenai | 0 | 281 |
| rprav007/snowflake-arctic-embed-m-finetuned-v1 | finetune | — | 109M | S | — | rprav007 | 0 | 273 |
| acpotts/finetuned_arctic | finetune | — | 109M | S | — | acpotts | 0 | 249 |
| Mdean77/legal-ft-1 | finetune | — | 109M | S | — | Mdean77 | 0 | 241 |
| ThakiCloud/SKILLRET-Edge-109M | finetune | — | 109M | S | apache-2.0 | ThakiCloud | 0 | 212 |
| vincha77/finetuned_arctic | finetune | — | 109M | S | — | vincha77 | 0 | 189 |
| rchrdgwr/finetuned-arctic-model | finetune | — | 109M | S | — | rchrdgwr | 0 | 188 |
| HuggingFaceFW-Dev/fine-pdfs-classification-teacher-eng_Latn-Qwen_Qwen3-235B-A22B-Instruct-2507 | finetune | — | 109M | S | apache-2.0 | HuggingFaceFW-Dev | 1 | 127 |
| versae/snowflake-arctic-embed-m-edu-scorer-lr3e4-bs32 | finetune | — | 109M | S | apache-2.0 | versae | 0 | 174 |
| philipk22/ind312-ft-v0 | finetune | — | 109M | S | — | philipk22 | 0 | 173 |
| mbudisic/snowflake-arctic-embed-m-ft-pstuts | finetune | — | 109M | S | — | mbudisic | 0 | 170 |
| Date | Commit | SHA |
|---|---|---|
| 2024-12-13 | add scarf | fc74610 |
| 2024-12-04 | Update README.md | 7802add |
| 2024-12-04 | Update README.md | 767e63c |
| 2024-12-02 | Update readme with infinity (#17) | cc17bea |
| 2024-11-22 | Update README.md | 3730650 |
| 2024-08-20 | Update README.md | e2b128b |
| 2024-08-20 | Update README.md | 6cebf51 |
| 2024-07-31 | Update README.md | 71bc94c |
| 2024-05-10 | Update README.md | 2ca412e |
| 2024-05-10 | Update README.md | 3bf73a0 |
| 2024-04-18 | Update README.md (#10) | 2169d31 |
| 2024-04-18 | Upload new ONNX weights (#9) | b88a9b1 |
| 2024-04-17 | Update README.md | 8d8c9ea |
| 2024-04-17 | Update README.md (#7) | 4a3e961 |
| 2024-04-17 | Delete onnx | 0202f57 |
| 2024-04-17 | Update model (previously incorrect) (#6) | 5f2e92c |
| 2024-04-16 | Update sentence_bert_config.json | c926fe6 |
| 2024-04-16 | Add example usage for transformers.js (#5) | a7ed5d0 |
| 2024-04-16 | Upload ONNX weights (#4) | e72201b |
| 2024-04-16 | Fix incorrect hyperlink in Model Card (#3) | 19cfd1d |
| 2024-04-16 | Sentence Transformers integration (#2) | ceb801b |
| 2024-04-16 | Update README.md | 5a14b88 |
| 2024-04-16 | Update README.md | 3076ecc |
| 2024-04-16 | Update README.md | 6205c72 |
| 2024-04-16 | Update README.md (#1) | 3d37d69 |
| 2024-04-16 | Update README.md | 25f813f |
| 2024-04-16 | Update README.md | d5643c7 |
| 2024-04-15 | Update README.md | 915c599 |
| 2024-04-15 | Update README.md | b30c8a2 |
| 2024-04-15 | Update README.md | 19f9227 |
Hosted endpoints observed for snowflake-arctic-embed-m, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| HF Inference hf | Snowflake/snowflake-arctic-embed-m | — | — | — | — | — | — | — | live | 2026-10-25 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:36 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:04 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.