Gemma 2 9B
Gemma 2 9B is an open-weights language model from Google, released June 24, 2024. It has 9.2B parameters (dense). On the Epoch Capabilities Index it scores 112.7, rank 201 of 256 rated models.
Check it against your own PC →
Can you run Gemma 2 9B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 5 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 5.2 GB | 5.3 GB | ~5 |
| 8 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 7.2 GB | 3.3 GB | ~7 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.5 GB | – | ~28 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.5 GB | – | ~38 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.5 GB | – | ~69 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 10.5 GB | – | ~120 |
Ready-made quantizations on Hugging Face: fedric95/gemma-2-9b-GGUF · QuantFactory/gemma-2-9b-GGUF · QuantFactory/magnum-v3-9b-customgemma2-GGUF · mradermacher/gemma-2-9b-i1-GGUF · QuantFactory/Apollo2-9B-GGUF · mradermacher/gemma-2-9b-GGUF
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 9.3 | MATH level 5, OTIS Mock AIME 2024-2025 |
| Knowledge | 24.9 | GPQA diamond, MMLU |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 62.8% |
| MATH level 5 | 21.0% |
| GPQA Diamond | 3.4% |
| OTIS Mock AIME | 0.5% |
Links
Hugging Face: google/gemma-2-9b · Epoch AI benchmarks
Models with a similar score
phi-3-small 7.4B · phi-3-medium 14B · Claude Instant · PaLM 2-L · Qwen2.5-Coder-14B · Mistral NeMo · Mixtral 8x7B · GPT-3.5 Turbo (Jan 2024)
More from Google
Gemini 4 Carbon · Gemini 4 Argon · Gemini 3.8 Flash · Gemini 3.7 Flash · Gemini 3.6 Flash · Gemini 3.5 Flash-Lite · Gemini 3.5 Flash Cyber · Gemma 4 E4B