gemma-7b
Params
8.5 B
Context
—
Downloads 30d
200 K
Likes
3,471
Commercial use: conditional · gemma
Gated — accept licence
GGUF · SAFETENSORS
View on Hugging Face ↗
Download history
daily snapshots · 7 days201 K150 K
Nov 4Nov 6Nov 8Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 17.1 GB | 20.6 GB | ⚠️ Tight — reduce context |
| gemma-7b.gguf | GGUF | 34.2 GB | 39.4 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run gemma:7b # pin the quantization explicitly $ ollama run gemma:7b-gguf
$ huggingface-cli download google/gemma-7b-GGUF \
gemma-7b.gguf --local-dir .
$ llama-cli -m gemma-7b.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/gemma-7b
{
"hf_id": "google/gemma-7b",
"params_b": 8.54,
"context_length": null,
"license": { "id": "gemma", "commercial": "conditional" },
"downloads_30d": 200487,
"vram_estimates": [
{ "quant": "GGUF", "gb": 39.4 },
{ "quant": "bf16", "gb": 20.6 }
],
"updated_at": "2026-11-04T01:00:19Z"
}
Specifications
- Architecture
- GemmaForCausalLM
- Parameters
- 8.5 B
- Tensor type
- BF16
- Licence
- gemma
- First seen on the Hub
- 2024-02-08
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-04
Compare with any text-generation model