FitMyLLM
Google/Dense

GoogleRecurrentGemma 9B

Griffin architecture — fixed-state recurrence, not attention. Constant RAM usage.

chat
9.63B
Parameters
8K
Context length
7
Benchmarks
6
Quantizations
Architecture
Dense
Released
2024-04-01
Layers
42
KV Heads
1
Head Dim
256
Family
gemma

Quantization Options

Context length:
QuantBitsVRAM @ 8KQuality
Q4_K_M4.89
6.5 GB
6.4 + 0.2 KV
good
Q5_K_S5.57
7.4 GB
7.2 + 0.2 KV
good
Q5_K_M5.7
7.5 GB
7.3 + 0.2 KV
good
Q6_K6.56
8.5 GB
8.4 + 0.2 KV
excellent
Q8_08.5
10.9 GB
10.7 + 0.2 KV
lossless
FP1616
19.9 GB
19.7 + 0.2 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run RecurrentGemma 9B now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (7)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# RecurrentGemma 9B is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=recurrentgemma-9b-it+GGUF), or use the vLLM tab with the original weights.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Apple M1 (8GB)
8 GB VRAM • 68 GB/s
APPLE
$499
Apple M2 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
Apple M3 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
NVIDIA Tesla K8
8 GB VRAM • 160 GB/s
NVIDIA
NVIDIA Tesla M60
8 GB VRAM • 160 GB/s
NVIDIA

Find the best GPU for RecurrentGemma 9B

Build Hardware for RecurrentGemma 9B
Spec sheet

RecurrentGemma 9B — 9.63B Dense.

Specifications
Parameters
9.63B
Architecture
Dense Transformer
Context Length
8K tokens
Capabilities
chat
Release Date
2024-04-01
Provider
Google
Family
gemma
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.896.4 GB94%
Q5_K_S5.577.2 GB96%
Q5_K_M5.77.3 GB96%
Q6_K6.568.4 GB97%
Q8_08.510.7 GB100%
FP161619.7 GB100%
Benchmark scores
MMLU-PRO37.4
MATH23.3
IFEval80.5
BBH44.2
GPQA12.8
MUSR12.2
BigCodeBench34.7
Compatible GPUs
30 @ Q4_K_M