Up to date
google Apache 2.0 out 5 years ago
132M parameters, text in, embeddings out. 1 provider serves it.
Verified 2026-10-25 Rank #62 in Embeddings · score 85.9 method v1 Sources 3 Downloads 30d 137.3k · #283 of 619 tracked
Picked by rule from 3 tracked pieces: the lab's own post, the most shared, a field report, the latest.
A GitHub repository hosts logos and metadata for thousands of financial institutions, including over 7,694 banks.
The 1 pick above, plus these 2. 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.
Weights only, an estimate: leave room for the KV cache. Method
About 0.1 GB at INT4, 0.2 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
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2022-03-02), amber triangles are 2 dated articles (each links to it).
16 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.
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 | feature-extraction |
|---|---|
| Library | transformers |
| Architectures | CanineModel |
| Model type | canine |
| Params by dtype | F32: 132,082,944 · I64: 16,384 |
| Size band | S |
| MoE | no |
| Papers | arXiv:2103.06874 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
Weights-only memory for canine-c: 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) | 0.2 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.
finetune: 15adapter: 1
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| Buseak/canine_deasciifier_final_0701_v8 | finetune | — | 132M | S | apache-2.0 | Buseak | 0 | 249 |
| addykan/model_data | finetune | — | 132M | S | apache-2.0 | addykan | 0 | 234 |
| humbleworth/domain-mlm | finetune | — | 132M | S | apache-2.0 | humbleworth | 0 | 167 |
| Anvilogic/CE-Typosquat-Detect | finetune | — | 132M | S | mit | Anvilogic | 0 | 100 |
| PaceKW/canine-c-multilabel-indonesian-hate-speech | finetune | — | 132M | S | apache-2.0 | PaceKW | 0 | 84 |
| PaceKW/canine-c-multilabel-indonesian-hate-speech-new-label | finetune | — | 132M | S | apache-2.0 | PaceKW | 0 | 73 |
| addykan/canine_100_chars | finetune | — | 132M | S | apache-2.0 | addykan | 0 | 67 |
| Anvilogic/Embedder-Typosquat-Detect | finetune | — | 132M | S | mit | Anvilogic | 1 | 6 |
| michal-tichy/canine-c-li | finetune | — | 132M | S | apache-2.0 | michal-tichy | 0 | 55 |
| michal-tichy/canine-c-multilabel-n-li | finetune | — | 132M | S | apache-2.0 | michal-tichy | 0 | 53 |
| michal-tichy/canine-c-multilabel-li | finetune | — | 132M | S | apache-2.0 | michal-tichy | 0 | 50 |
| addykan/canine-rando | finetune | — | 132M | S | apache-2.0 | addykan | 0 | 48 |
| addykan/canine-rando-30-chars-5-epoch | finetune | — | 132M | S | apache-2.0 | addykan | 0 | 48 |
| PaceKW/canine-c-fine-tuned-hs-new | finetune | — | 132M | S | apache-2.0 | PaceKW | 0 | 33 |
| VohraAK/canine-tydiqa | adapter | — | — | — | apache-2.0 | VohraAK | 0 | 32 |
| addykan/canine-rando-30-chars | finetune | — | 132M | S | apache-2.0 | addykan | 0 | 29 |
Hosted endpoints observed for canine-c, 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 | google/canine-c | — | — | — | — | — | — | — | 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 · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-14 14:07 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.
