- 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
- Kind
- Base model (no base model declared on the Hub)Gemma2ForCausalLM
- On Hugging Face
- google/gemma-2-9b18k downloads in the last 30 days, 747 likes
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
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.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 2.0 GB, worked out from the model's config (zaid646/gemma-2-9b-awq), 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
fedric95/gemma-2-9b-GGUF (converted by fedric95), 1.7k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 3.5 GBfile size | 6.0 GB3.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q2_KOllama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q2_KDownload hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q2_K.gguf" --local-dir gemma-2-9b-GGUF |
| Q3_K_S | 4.0 GBfile size | 6.5 GB4.0 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q3_K_SOllama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q3_K_SDownload hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q3_K_S.gguf" --local-dir gemma-2-9b-GGUF |
| Q3_K_M | 4.4 GBfile size | 6.9 GB4.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q3_K_MOllama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q3_K_MDownload hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q3_K_M.gguf" --local-dir gemma-2-9b-GGUF |
| Q3_K_L | 4.8 GBfile size | 7.2 GB4.8 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q3_K_LOllama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q3_K_LDownload hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q3_K_L.gguf" --local-dir gemma-2-9b-GGUF |
| Q4_K_S | 5.1 GBfile size | 7.6 GB5.1 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q4_K_SOllama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q4_K_SDownload hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q4_K_S.gguf" --local-dir gemma-2-9b-GGUF |
| Q4_K_M | 5.4 GBfile size | 7.8 GB5.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q4_K_MOllama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q4_K_MDownload hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q4_K_M.gguf" --local-dir gemma-2-9b-GGUF |
| Q5_K_S | 6.0 GBfile size | 8.5 GB6.0 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q5_K_SOllama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q5_K_SDownload hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q5_K_S.gguf" --local-dir gemma-2-9b-GGUF |
| Q5_K_M | 6.2 GBfile size | 8.7 GB6.2 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q5_K_MOllama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q5_K_MDownload hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q5_K_M.gguf" --local-dir gemma-2-9b-GGUF |
| Q6_K | 7.1 GBfile size | 9.5 GB7.1 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q6_KOllama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q6_KDownload hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q6_K.gguf" --local-dir gemma-2-9b-GGUF |
| Q8_0 | 9.2 GBfile size | 11.6 GB9.2 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:Q8_0Ollama ollama run hf.co/fedric95/gemma-2-9b-GGUF:Q8_0Download hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b-Q8_0.gguf" --local-dir gemma-2-9b-GGUF |
| F32 | 34.4 GBfile size | 36.9 GB34.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf fedric95/gemma-2-9b-GGUF:F32Ollama ollama run hf.co/fedric95/gemma-2-9b-GGUF:F32Download hf download fedric95/gemma-2-9b-GGUF --include "gemma-2-9b.FP32.gguf" --local-dir gemma-2-9b-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| F32original weights | 34.4 GBfile size | 36.9 GB34.4 + 2.0 + 0.50 |
hf download google/gemma-2-9b --local-dir gemma-2-9bOther conversions (7; sizes not read)
- unsloth/gemma-2-9b-bnb-4bit bitsandbytes, 4bit, 10k downloads
- gunho1123/gemma-2-9b-anybcq2to4-g128 Other, 15 downloads
- GuillermoBarrio/gemma-2-9b-electoral-2019 bitsandbytes, 9 downloads
- zaid646/gemma-2-9b-awq AWQ, 9 downloads
- mssfj/gemma-2-9b-bnb-4bit-chat-template bitsandbytes, 4bit, 7 downloads
- leliuga/gemma-2-9b-bnb-4bit bitsandbytes, 4bit, 6 downloads
- altomek/gemma-2-9b-8bpw-EXL2 EXL2, 5 downloads
The Hub tags 55 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.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- google/gemma-2-9b-it9.2B163kReviewed
- Unbabel/Tower-Plus-9B9.2B20kUnreviewed
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.