Next-1B is a 1-billion parameter causal language model based on Gemma 3, designed for efficiency, low-resource deployment, and reasoning-focused natural language understanding. Extremely lightweight — can run on consumer GPUs with low VRAM. Optimized for text reasoning, summarization, and creative generation. Supports Turkish natively while remaining multilingual. Open-source and transparent for research and applications. Ideal for developers, students, and organizations needing fast, reliable, and low-resource text-generation. 1. Lightweight Efficiency: Run smoothly on low-resource devices. 2. Reasoning-Focused: Provide logical and coherent text outputs. 3. Accessibility: Fully open-source…
[Gemma 3 Technical Report][g3-tech-report] [Responsible Generative AI Toolkit][rai-toolkit] [Gemma on Kaggle][kaggle-gemma] [Gemma on Vertex Model Garden][vertex-mg-gemma3] Summary description and brief definition of inputs and outputs.
Parameters1B
Context—
Weights2.0 GB
Licensegemma
AccessAccess requested at publisher
Monthly Downloads3M
Runs On
What it takes to serve gemma-3-1b-it (1B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 2.0 GB | 2.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.0 GB | 1.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.5 GB | 0.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
SAVRN's Notes on gemma-3-1b-it
At 16-bit the memory bill for this instruction-tuned text generator is 2.4 GB, and at 4-bit it is 0.6 GB. The cheapest card on our Index that clears either is one MI300X, 192 GB at $1.85 an hour on-demand, so the hourly price reflects the card market, not anything a 1B-parameter model needs. The 8-bit build lands at 1.2 GB. It shares a card you already own; nobody provisions a machine for it.
Access is gated: the files come from Google once you accept the Gemma Terms of Use, which allow commercial use and redistribution but attach the Prohibited Use Policy to every copy you distribute. Fine-tune it, ship it inside a product, and those restrictions ship too. It derives from gemma-3-1b-pt, the base for your own instruction tuning. The page lists no context length for this checkpoint and no host prices, so confirm the window before sizing prompts.
Model Card
[Gemma 3 Technical Report][g3-tech-report] [Responsible Generative AI Toolkit][rai-toolkit] [Gemma on Kaggle][kaggle-gemma] [Gemma on Vertex Model Garden][vertex-mg-gemma3] Summary description and brief definition of inputs and outputs. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous…
Excerpt from the card by Google, licensed gemma.
Identity and Version
- Repository
- google/gemma-3-1b-it
- Publisher
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 1B parameters
- Languages
- Not stated by the source
- Revision
- dcc83ea841ab6100d6b47a070329e1ba4cf78752
- First published
- 2025-03-10
- Last updated
- 2025-04-04
Files and Weights
10 files, 2.0 GB in total. The weights are 1 file totalling 2.0 GB in safetensors.
Weights1 file · 2.0 GB
Configuration4 files · 1.8 KB
Tokenizer3 files · 39.2 MB
Documentation1 file · 24.3 KB
Repository1 file · 1.7 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 2.0 GB | — |
| added_tokens.json | Configuration | 35 B | — |
| config.json | Configuration | 899 B | — |
| generation_config.json | Configuration | 215 B | — |
| special_tokens_map.json | Configuration | 662 B | — |
| README.md | Documentation | 24.3 KB | — |
| .gitattributes | Repository | 1.7 KB | — |
| tokenizer.json | Tokenizer | 33.4 MB | — |
| tokenizer.model | Tokenizer | 4.7 MB | — |
| tokenizer_config.json | Tokenizer | 1.2 MB | — |
License and Download
- License
- gemma
- Access
- Access requested at publisher
- Download size
- 2.0 GB
Download from Google
Released by Google through Kaggle.
Built From
- Derived from google/gemma-3-1b-pt
- Described by arXiv:1705.03551
- Described by arXiv:1810.12440
- Described by arXiv:1903.00161
- Described by arXiv:1904.09728
- Described by arXiv:1905.07830
- Described by arXiv:1905.10044
- Described by arXiv:1907.10641
- Described by arXiv:1908.02660
- Described by arXiv:1910.11856
- Described by arXiv:1911.01547
- Described by arXiv:1911.11641
- Described by arXiv:2009.03300
- Described by arXiv:2103.03874
- Described by arXiv:2104.12756
- Described by arXiv:2106.03193
- Described by arXiv:2107.03374
- Described by arXiv:2108.07732
- Described by arXiv:2110.14168
- Described by arXiv:2203.10244
- Described by arXiv:2210.03057
- Described by arXiv:2304.06364
- Described by arXiv:2311.12022
- Described by arXiv:2311.16502
- Described by arXiv:2312.11805
- Described by arXiv:2404.12390
- Described by arXiv:2404.16816
- Described by arXiv:2502.12404
- Described by arXiv:2502.21228
Evaluations
Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| Idavidrein/gpqa | Task diamondMetric diamondSetup GPQA DiamondComparison conditions not established | 24.7475 | EvalEval Reported by a third party |
Evaluated revision not stated | 2026-04-16 |
| Idavidrein/gpqa | Task mainMetric mainSetup GPQA chain-of-thoughtComparison conditions not established | 16.8161 | EvalEval Reported by a third party |
Evaluated revision not stated | 2026-06-30 |
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.0 GB |
| 16-bit | 2.0 GB |
| 8-bit | 1.0 GB |
| 4-bit | 0.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Built on This Model
- Merged fromQemma-Q14B
- Derived fromQemma-Q14B
- Merged fromQemma-Q1.7B
- Derived fromQemma-Q1.7B
Compare gemma-3-1b-it
Questions About gemma-3-1b-it
How much GPU memory does gemma-3-1b-it need?
About 2.4 GB at 16-bit and 0.6 GB at 4-bit: the weights (1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gemma-3-1b-it on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use gemma-3-1b-it commercially?
Yes, with conditions. gemma-3-1b-it is released under Gemma Terms of Use. Gemma models are released under Google's Gemma Terms of Use, which permit commercial use and redistribution subject to the Gemma Prohibited Use Policy, whose restrictions must be passed on to anyone the model is distributed to.
Similar Models
My mathematical formulation to utilize space projections to "measure" the Jump between points of discontinuity found in Non-Differentialable Functions. This Model underwent an additional merge between Qemma-redux and Qwen3-1.7B, in addition to adding Rope Scaling. Fusion Logic was updated to aid per layer fusion and post fusion embedding alignment. Qemma is a HuggingFace-native hybrid model that merges Gemma-3 (1B) and Qwen-3 (1.7B) at the weight level (no adapters). This variant uses Yarn based Rope Scaling with 1: Ratio from maxpositionembeddings = 242144 Gemma-3 backbone (26 layers, hidden 1152, MLP 6912) Qwen-style attention regrouped to Gemma’s 4×256 heads. (headdim=128, hidden=2048…
My mathematical formulation to utilize space projections to "measure" the Jump between points of discontinuity found in Non-Differentialable Functions. This Model underwent an additional merge between Qemma-redux and Qwen3-0.6B, in addition to adding Rope Scaling. Fusion Logic was updated to aid per layer fusion and post fusion embedding alignment. Qemma is a HuggingFace-native hybrid model that merges Gemma-3 (1B) and Qwen-3 (0.6B) at the weight level (no adapters). This variant uses Yarn based Rope Scaling with 1:1 Ratio from maxpositionembeddings Use: research, instruction following, code/help, analysis, further SFT/RLHF. Limits: may hallucinate; not for safety-critical, medical, legal…
My mathematical formulation to utilize space projections to "measure" the Jump between points of discontinuity found in Non-Differentialable Functions. This Model underwent an additional merge between Qemma-redux and Qwen3-14B, in addition to adding Rope Scaling. Fusion Logic was updated to aid per layer fusion and post fusion embedding alignment. Qemma is a HuggingFace-native hybrid model that merges Gemma-3 (1B) and Qwen-3 (14B) at the weight level (no adapters). This variant uses Yarn based Rope Scaling with 1: Ratio from maxpositionembeddings = 524288 Gemma-3 backbone (26 layers, hidden 1152, MLP 6912) Qwen-style attention regrouped to Gemma’s 4×256 heads. (headdim=128, hidden=5120…
This repository contains a text-only Mini-K3-1H v2 pretraining checkpoint from a controlled 20-architecture comparison. The family retains Kimi-K3's KDA and Gated MLA operators, block Attention Residuals, Stable LatentMoE, SiTU activations, output gates, and Quantile Balancing at approximately one billion logical parameters. The exact architecture for this repository is listed below; some ablations deliberately replace the baseline KDA/MLA ratio, decay granularity, convolution length, or positional encoding. - Hidden width / attention heads / KDA head width: 1024 / 12 / 128 - Vocabulary / BOS / generation EOS / PAD: 163840 / 163584 / 163586 / 163839 control state retained in FP32 where…
Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, Mohammad Rastegari We introduce OpenELM, a family of Open Efficient Language Models. OpenELM uses a layer-wise scaling strategy to efficiently allocate parameters within each layer of the transformer model, leading to enhanced accuracy. We pretrained OpenELM models using the CoreNet library. We release both pretrained and instruction tuned models with 270M, 450M, 1.1B and 3B parameters. We release the complete framework, encompassing data preparation, training, fine-tuning, and evaluation procedures, alongside multiple pre-trained…