Up to date
google Gemma Terms of Use out 3 years ago
8.54B parameters, text in, text out, 8K tokens of context.
Verified 2026-10-26 07:27 UTC Rank #612 in LLMs · score 73.8 method v1 Sources 3 Downloads 30d 4.6k · #549 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: NiansuhAI/HFLLMs ♥ 30 · Hansimov/hf-llm-api ♥ 20 · Justinrune/LLaMA-Factory ♥ 12 · NiansuhAI/Main ♥ 10
Weights only, an estimate: leave room for the KV cache. Method
About 5.1 GB at INT4, 10 GB at FP8, 21 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.
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 LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | GemmaForCausalLM |
| Model type | gemma |
| Dtype | bfloat16 |
| Params by dtype | BF16: 8,537,680,896 |
| 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 | 2026-10-26 |
vLLM: supported · GemmaForCausalLM · 4b1c04e76fe9ac3ca8b7e541dd423e7d5f38dc60SGLang: supported · GemmaForCausalLM · 60d941293e3af27a12c6eb64e2c3e2e1a17f100f
vLLM registry (4b1c04e76fe9ac3ca8b7e541dd423e7d5f38dc60) · SGLang registry (60d941293e3af27a12c6eb64e2c3e2e1a17f100f) · 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-1.1-7b-it: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 21 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 10 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 5.1 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
finetune: 7quantized: 6adapter: 3
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| lemon-mint/gemma-7b-openhermes-v0.80 | finetune | — | 8.54B | M | gemma | lemon-mint | 1 | 75.2k |
| lemon-mint/gemma-ko-7b-instruct-v0.71 | finetune | — | 8.54B | M | gemma | lemon-mint | 1 | 37.2k |
| second-state/gemma-1.1-7b-it-GGUF | quantized | GGUF | — | — | gemma | second-state | 0 | 11.3k |
| mradermacher/gemma-1.1-7b-it-i1-GGUF | quantized | GGUF | — | — | gemma | mradermacher | 0 | 5.2k |
| mradermacher/gemma-1.1-7b-it-GGUF | quantized | GGUF | — | — | gemma | mradermacher | 0 | 2.6k |
| tensorblock/gemma-1.1-7b-it-GGUF | quantized | GGUF | — | — | gemma | tensorblock | 0 | 1.9k |
| zeromodels/gemma-1.1-7b-it | finetune | — | — | — | gemma | zeromodels | 0 | 436 |
| IsakNordgren/gemma-1.1-7b-it-x2 | finetune | — | 7.24B | M | — | IsakNordgren | 0 | 166 |
| chenghenry/gemma-1.1-7b-it-GGUF | quantized | GGUF | — | — | gemma | chenghenry | 0 | 158 |
| brildev7/gemma-1.1-7b-it-translation-koen-sft-qlora | adapter | — | — | — | — | brildev7 | 2 | 45 |
| EricB/gemma-1.1-7b-it-UQFF | quantized | — | — | — | — | EricB | 0 | 135 |
| yzhuang/gemma-1.1-7b-it_fictional_chinese_v1 | finetune | — | 8.54B | M | gemma | yzhuang | 1 | 81 |
| aidiary/gemma-7b-finetune-gozarinnemon | adapter | — | — | — | gemma | aidiary | 0 | 70 |
| yzhuang/gemma-1.1-7b-it_fictional_Korean_v1 | finetune | — | 8.54B | M | gemma | yzhuang | 0 | 67 |
| Kubermatic/DeepCNCF | adapter | — | — | — | mit | Kubermatic | 0 | 54 |
| yzhuang/gemma-1.1-7b-it_fictional_English_v1 | finetune | — | 8.54B | M | gemma | yzhuang | 0 | 46 |
| Date | Commit | SHA |
|---|---|---|
| 2024-06-27 | Update link to terms (#22) | 065a528 |
| 2024-04-16 | Fix slow tokenizer (#14) | 16128b0 |
| 2024-04-11 | Update benchmark scores and averages for 1.1 | 689f62a |
| 2024-04-05 | Update README (#8) | 4b617e4 |
| 2024-04-05 | Update README (#5) | d415e88 |
| 2024-04-05 | Update README (#4) | 1db8a3b |
| 2024-04-04 | Model card and tokenizer (#2) | abe048c |
| 2024-04-03 | Update Weights (#1) | c2e659a |
| 2024-03-26 | Upload folder using huggingface_hub | 5962f7e |
| 2024-03-26 | initial commit | af26a94 |
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: 2026-10-26 · HF API: 2026-10-26 07:22 UTC · Providers: 2026-10-26 07:26 UTC · Articles: 2026-10-26 07:27 UTC · Summary: 2026-10-07 15:12 UTC · Last verified 2026-10-26 07:27 UTC
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
