Up to date
google Gemma Terms of Use out 3 years ago
2.51B parameters, text in, text out, 8K tokens of context.
Verified 2026-10-25 Rank #645 in LLMs · score 73.2 method v1 Sources 3 Downloads 30d 16.8k · #470 of 619 tracked
Picked by rule from 1 tracked piece: the lab's own post, the most shared, a field report, the latest.
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: 6 quantized builds and 100 Spaces.
Top Spaces running it: KingNish/Very-Fast-Chatbot ♥ 46 · NiansuhAI/HFLLMs ♥ 30 · GenAICoder/MultiPDFChatbot ♥ 20 · Justinrune/LLaMA-Factory ♥ 12
Weights only, an estimate: leave room for the KV cache. Method
About 1.5 GB at INT4, 3.0 GB at FP8, 6.0 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 (2024-03-26), amber triangles are 1 dated article (each links to it), grey ticks are repo commits.
54 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 | GemmaForCausalLM |
| Model type | gemma |
| Dtype | bfloat16 |
| Params by dtype | BF16: 2,506,172,416 |
| Size band | M |
| MoE | no |
| Context length | 8,192 (config.json max_position_embeddings) |
| Gated | manual |
| Papers | arXiv:2312.11805, arXiv:2009.03300, arXiv:1905.07830, arXiv:1911.11641, arXiv:1904.09728, arXiv:1905.10044, arXiv:1907.10641, arXiv:1811.00937, arXiv:1809.02789, arXiv:1911.01547, arXiv:1705.03551, arXiv:2107.03374, arXiv:2108.07732, arXiv:2110.14168, arXiv:2304.06364, arXiv:2206.04615, arXiv:1804.06876, arXiv:2110.08193 |
| License | Gemma Terms of Use (gemma) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · GemmaForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · GemmaForCausalLM · 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 gemma-1.1-2b-it: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 6.0 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 3.0 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 1.5 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
merge: 7quantized: 6finetune: 16adapter: 25
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| lemon-mint/gemma-ko-1.1-2b-it | merge | — | 2.51B | M | gemma | lemon-mint | 1 | 39.2k |
| second-state/gemma-1.1-2b-it-GGUF | quantized | GGUF | — | — | gemma | second-state | 0 | 7.1k |
| MaziyarPanahi/gemma-1.1-2b-it-GGUF | quantized | GGUF | — | — | — | MaziyarPanahi | 0 | 6.1k |
| mradermacher/gemma-1.1-2b-it-i1-GGUF | quantized | GGUF | — | — | gemma | mradermacher | 0 | 5.2k |
| SicariusSicariiStuff/2B_or_not_2B | finetune | — | 2.51B | M | gemma | SicariusSicariiStuff | 26 | 2.7k |
| lemon-mint/gemma-2b-translation-v0.90 | finetune | — | 2.51B | M | gemma | lemon-mint | 0 | 4k |
| lemon-mint/gemma-2b-translation-v0.131 | finetune | — | 2.51B | M | gemma | lemon-mint | 0 | 4k |
| mradermacher/gemma-1.1-2b-it-GGUF | quantized | GGUF | — | — | gemma | mradermacher | 0 | 2.5k |
| featherless-ai-quants/google-gemma-1.1-2b-it-GGUF | quantized | GGUF | — | — | — | featherless-ai-quants | 0 | 2k |
| cat-searcher/gemma-1.1-2b-it-sppo-iter0-evol-mixed | finetune | — | 2.51B | M | gemma | cat-searcher | 0 | 1.6k |
| BSVGK/gemma-1.1-2b-it-drugbank-kg2text-merged-v2 | adapter | — | 2.51B | M | mit | BSVGK | 1 | 958 |
| aiqwe/gemma-2b-it-example-v1 | adapter | — | — | — | gemma | aiqwe | 0 | 842 |
| andreass123/gemma-ko-1.1-2b-it-2-Q4_K_M-GGUF | merge | GGUF | — | — | gemma | andreass123 | 0 | 760 |
| mnsims1024/TallGemma-Raw | merge | — | 6.47B | M | — | mnsims1024 | 0 | 701 |
| lemon-mint/gemma-2b-translation-v0.140 | finetune | — | 2.51B | M | gemma | lemon-mint | 0 | 599 |
| lemon-mint/gemma-2b-translation-v0.91 | finetune | — | 2.51B | M | gemma | lemon-mint | 0 | 593 |
| lemon-mint/gemma-2b-translation-v0.92 | finetune | — | 2.51B | M | gemma | lemon-mint | 0 | 569 |
| Recaru/gemma-ko-1.1-2b-it-Q5_K_M-GGUF | merge | GGUF | — | — | gemma | Recaru | 0 | 506 |
| RituGujela100/gemma-qlora-customer-support | finetune | — | 2.51B | M | mit | RituGujela100 | 0 | 428 |
| lemon-mint/gemma-2b-diff-model | merge | — | 2.51B | M | gemma | lemon-mint | 0 | 424 |
| ScienceArtMagic/TallGemma-Raw | merge | — | 6.47B | M | — | ScienceArtMagic | 0 | 248 |
| mlx-community/gemma-1.1-2b-it-bf16 | finetune | -bf16 | 2.51B | M | gemma | mlx-community | 0 | 230 |
| Pisethan/khmer-gemma-lesson-lora | adapter | — | — | — | — | Pisethan | 0 | 175 |
| EricB/gemma-1.1-2b-it-UQFF | quantized | — | — | — | — | EricB | 0 | 161 |
| Venkatesh4342/gemma-1.1-2b-it-code2instruct | adapter | — | — | — | gemma | Venkatesh4342 | 0 | 151 |
| RituGujela100/gemma-qlora-customer-support-v2.0 | finetune | — | 2.51B | M | mit | RituGujela100 | 0 | 148 |
| zeromodels/gemma-1.1-2b-it | finetune | — | — | — | gemma | zeromodels | 0 | 142 |
| ihork/gm1.1-2it-ft2 | adapter | — | — | — | gemma | ihork | 0 | 112 |
| lemon-mint/gemma-ko-1.1-2b-it-2 | merge | — | 2.51B | M | gemma | lemon-mint | 1 | 59 |
| sanjaydasgupta/s11a-to-json-gemma-2b-it | adapter | — | — | — | — | sanjaydasgupta | 0 | 96 |
| BSVGK/gemma-1.1-2b-it-drugbank-kg2text-lora-v2 | adapter | — | — | — | mit | BSVGK | 0 | 77 |
| JosephLee/science_textbook_gemma_2B | adapter | — | — | — | — | JosephLee | 0 | 73 |
| ilkeileri/gemma-sales-comprehensive | adapter | — | — | — | apache-2.0 | ilkeileri | 0 | 68 |
| ndr12/gemmatrain | finetune | — | 2.51B | M | apache-2.0 | ndr12 | 0 | 56 |
| FaustusFaber31/gemma-4-E4B-it-awq-int4-xlam | finetune | awq | — | — | gemma | FaustusFaber31 | 1 | 0 |
| Eya0910/finetuned-gemma3 | adapter | — | 2.51B | M | — | Eya0910 | 0 | 44 |
| appohfaiths/gemma-edu-med | finetune | — | 2.51B | M | gemma | appohfaiths | 0 | 43 |
| date3k2/gemma-2b-it-sft-vi-alpaca | adapter | — | — | — | gemma | date3k2 | 0 | 42 |
| BotatoFontys/FinetunedModel | adapter | — | 2.55B | M | gemma | BotatoFontys | 0 | 41 |
| LINGESH-7/Gemma-1.1-2B-Instruct-FT-harpomaxx-unix-commands | adapter | — | — | — | other | LINGESH-7 | 0 | 41 |
| Date | Commit | SHA |
|---|---|---|
| 2024-06-27 | Update link to terms (#17) | d750f5e |
| 2024-04-16 | Fix tokenizer (#13) | bf4924f |
| 2024-04-11 | Update benchmark scores and averages for 1.1 | 28d20bc |
| 2024-04-05 | Update README (#10) | 1ef79cc |
| 2024-04-05 | Update README (#7) | 361dc59 |
| 2024-04-05 | Update README (#6) | 8cbb605 |
| 2024-04-04 | Update README (#4) | e582a4f |
| 2024-04-03 | Model card (#2) | 2dcbbb4 |
| 2024-04-03 | config-updates (#1) | d7f3260 |
| 2024-04-03 | Update Weights (#3) | 70802db |
| 2024-03-26 | Upload folder using huggingface_hub | 36772d4 |
| 2024-03-26 | initial commit | e18302d |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency.
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 21:40 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:12 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.
