- Size
- 9.2B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Gemma Terms of UseOur reading, check the licence: Commercial use is allowed with no user or revenue cap, but the Gemma Prohibited Use Policy (a separate document, not in this text) is part of the terms, and you must pass the use restrictions on as enforceable terms to anyone you distribute to. Models distilled from Gemma or trained on its outputs to perform like it count as Model Derivatives and stay under these terms, and Google may restrict use remotely if it believes the terms are broken. The page says these terms cover the models in its appendix (Gemma 1 to 3, 3n and variants) and that Gemma 4 has a separate licence.
- On the Hub since
- 24 Jun 2024the date the repo was created
- Context length
- Not known
- Fine-tune
- of google/gemma-2-9bGemma2ForCausalLM
- On Hugging Face
- google/gemma-2-9b-it163k downloads in the last 30 days, 1.2k likes
Scores
- default setting27.5%±2.327 Jan 2025, log
Epoch's name: gemma-2-9b-it. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- default setting21.0%±0.927 Jan 2025, log
Epoch's name: gemma-2-9b-it. Best closed model on this set: gpt-5-2025-08-07_high, 98.1% (OpenAI). All 108 results
- default setting0.6%±0.47 Mar 2025, log
Epoch's name: gemma-2-9b-it. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- default setting28.7%LiveBench Leaderboard
Epoch's name: gemma-2-9b-it. Best closed model on this set: gemini-2.5-pro-exp-03-25, 82.3% (Google DeepMind). All 54 results
- Shots: 572.1%Stanford CRFM Leaderboard
Epoch's name: gemma-2-9b-it. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 2.6 GB, worked out from the model's config (hugging-quants/gemma-2-9b-it-AWQ-INT4), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
bartowski/gemma-2-9b-it-GGUF (converted by bartowski), 32k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 3.5 GBfile size | 6.7 GB3.5 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:IQ3_XXSOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:IQ3_XXSDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-IQ3_XXS.gguf" --local-dir gemma-2-9b-it-GGUF |
| IQ3_XS | 3.9 GBfile size | 7.0 GB3.9 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:IQ3_XSOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:IQ3_XSDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-IQ3_XS.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q3_K_S | 4.0 GBfile size | 7.2 GB4.0 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q3_K_SOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q3_K_SDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q3_K_S.gguf" --local-dir gemma-2-9b-it-GGUF |
| IQ3_M | 4.2 GBfile size | 7.3 GB4.2 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:IQ3_MOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:IQ3_MDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-IQ3_M.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q3_K_M | 4.4 GBfile size | 7.6 GB4.4 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q3_K_MOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q3_K_MDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q3_K_M.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q3_K_L | 4.8 GBfile size | 7.9 GB4.8 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q3_K_LOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q3_K_LDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q3_K_L.gguf" --local-dir gemma-2-9b-it-GGUF |
| IQ4_XS | 4.8 GBfile size | 8.0 GB4.8 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:IQ4_XSOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:IQ4_XSDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-IQ4_XS.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q3_K_XL | 5.0 GBfile size | 8.1 GB5.0 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q3_K_XLOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q3_K_XLDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q3_K_XL.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q4_K_S | 5.1 GBfile size | 8.2 GB5.1 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q4_K_SOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q4_K_SDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q4_K_S.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q4_K_M | 5.4 GBfile size | 8.5 GB5.4 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q4_K_MOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q4_K_MDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q4_K_M.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q4_K_L | 5.6 GBfile size | 8.7 GB5.6 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q4_K_LOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q4_K_LDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q4_K_L.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q5_K_S | 6.0 GBfile size | 9.2 GB6.0 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q5_K_SOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q5_K_SDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q5_K_S.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q5_K_M | 6.2 GBfile size | 9.3 GB6.2 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q5_K_MOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q5_K_MDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q5_K_M.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q5_K_L | 6.4 GBfile size | 9.5 GB6.4 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q5_K_LOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q5_K_LDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q5_K_L.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q6_K | 7.1 GBfile size | 10.2 GB7.1 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q6_KOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q6_KDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q6_K.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q6_K_L | 7.3 GBfile size | 10.4 GB7.3 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q6_K_LOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q6_K_LDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q6_K_L.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q8 | 7.3 GBfile size | 10.4 GB7.3 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q8Ollama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q8Download hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q6_K-Q8.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q8_0 | 9.2 GBfile size | 12.3 GB9.2 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q8_0Ollama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q8_0Download hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q8_0.gguf" --local-dir gemma-2-9b-it-GGUF |
| F16 | 10.0 GBfile size | 13.1 GB10.0 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:F16Ollama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:F16Download hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q8_0-f16.gguf" --local-dir gemma-2-9b-it-GGUF |
| Q8_0_L | 10.0 GBfile size | 13.1 GB10.0 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:Q8_0_LOllama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q8_0_LDownload hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q8_0_L.gguf" --local-dir gemma-2-9b-it-GGUF |
| F32 | 34.4 GBfile size | 37.6 GB34.4 + 2.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/gemma-2-9b-it-GGUF:F32Ollama ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:F32Download hf download bartowski/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-f32.gguf" --local-dir gemma-2-9b-it-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXTheBlueObserver/gemma-2-9b-it-MLX-104ce | 3.8 GBfile size | 6.9 GB3.8 + 2.6 + 0.50 | Download page |
| MLX 6bitmlx-community/gemma-2-9b-it-6bit | 7.0 GBfile size | 10.1 GB7.0 + 2.6 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 17.2 GBfile size | 20.3 GB17.2 + 2.6 + 0.50 |
hf download google/gemma-2-9b-it --local-dir gemma-2-9b-itOther conversions (9; sizes not read)
- hugging-quants/gemma-2-9b-it-AWQ-INT4 AWQ, int4, 799k downloads
- unsloth/gemma-2-9b-it-bnb-4bit bitsandbytes, 4bit, 9.4k downloads
- RedHatAI/gemma-2-9b-it-FP8 FP8, 821 downloads
- RedHatAI/gemma-2-9b-it-quantized.w8a16 Other, 660 downloads
- solidrust/gemma-2-9b-it-AWQ AWQ, 413 downloads
- mlc-ai/gemma-2-9b-it-q4f16_1-MLC Other, 388 downloads
- mlc-ai/gemma-2-9b-it-q4f32_1-MLC Other, 308 downloads
- OpenVINO/gemma-2-9b-it-int4-ov Other, int4, 79 downloads
- qilowoq/gemma-2-9B-it-4Bit-GPTQ GPTQ, 4bit, 26 downloads
The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.