Up to date
14.0B parameters, text in, text out.
Verified 2026-10-25 Rank #742 in LLMs · score 71.6 method v1 Sources 3 Downloads 30d 13.5k · #483 of 619 tracked
Picked by rule from 19 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Phi-3 models achieve high performance rivaling Mixtral 8x7B by training on a scaled-up dataset of heavily filtered publicly available web data and synthetic data.
Microsoft released the Phi family of open-source small language models, which are the most capable and cost-effective SLMs available.
The 2 picks above, plus these 17. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
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.
No API provider serves it, so its downloads are people running it themselves: 21 quantized builds.
Weights only, an estimate: leave room for the KV cache. Method
About 8.4 GB at INT4, 17 GB at FP8, 34 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 (2024-05-07), amber triangles are 10 dated articles (each links to it).
151 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 LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | Phi3ForCausalLM |
| Model type | phi3 |
| Params by dtype | BF16: 13,960,238,080 |
| Size band | L |
| MoE | no |
| License | MIT (mit) |
| Hub snapshot | 2026-10-25 |
Weights-only memory for Phi-3-medium-4k-instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 34 GB · Single high-end GPU (<80 GB) |
|---|---|
| FP8 (1 byte/param) | 17 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 8.4 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 21adapter: 25finetune: 104merge: 1
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.
Hub snapshot: 2026-10-25 · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-14 14:08 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.
