Gemma 1.1 2B
Google · dense · 2.5B parameters · 8,192 context
Parameters
2.5B
Context Window
8K tokens
Architecture
Dense
Best GPU
RTX 3080
Intelligence Brief
Gemma 1.1 2B is a 2.5B parameter DENSE model from Google, featuring Grouped Query Attention (GQA) with 18 layers and 2,048 hidden dimensions. With a 8,192 token context window, it supports code. For self-hosted inference, RTX 3080 delivers optimal throughput at $133/month.
Recent changes
Loading…
Related models
5 suggestions- CodeGemma 7BGemma · 8.5B—
- Gemma 2 2BGemma 2 · 2.6B—
- Gemma 3 2BGemma 3 · 2B—
- Gemma 3 4BGemma 3 · 4.3B$0.080/M out
- PaLI-Gemma 3BPaLI-Gemma · 2.9B—
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
5.0 GB
FP8 Weights
2.5 GB
INT4 Weights
1.3 GB
GPU Compatibility Matrix
Gemma 1.1 2B is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
738.7 tok/s
Latency (ITL)
1.4ms
Est. TTFT
0ms
Cost/Month
$133
Cost/M Tokens
$0.07
BF16 · 1 GPU · vllm
100/100
score
Throughput
264.4 tok/s
Latency (ITL)
3.8ms
Est. TTFT
1ms
Cost/Month
$209
Cost/M Tokens
$0.30
BF16 · 1 GPU · vllm
100/100
score
Throughput
435.4 tok/s
Latency (ITL)
2.3ms
Est. TTFT
0ms
Cost/Month
$85
Cost/M Tokens
$0.07
Deployment Options
API Deployment
No API pricing available
Single GPU
RTX 3080
$133/mo
Min VRAM: 3 GB
Multi-GPU
RTX 3080
738.7 tok/s
Best available config
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (RTX 3080, BF16)
Precision Impact
bf16
5.0 GB
weights/GPU
~738.7 tok/s
fp8
2.5 GB
weights/GPU
int4
1.3 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Gemma 1.1 2B
Self-Hosted Infrastructure
Similar Models
Gemma 2 2B
2.6B params · dense
Quality: 44
RecurrentGemma 2B
2.7B params · dense
Quality: 50
SeamlessM4T v2 Large
2.3B params · dense
Quality: 50
Phi 2
2.7B params · dense
Quality: 50
Qwen 2 VL 2B
2.2B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does Gemma 1.1 2B need for inference?
Gemma 1.1 2B requires approximately 5.0 GB of VRAM at BF16 precision, 2.5 GB at FP8, or 1.3 GB at INT4 quantization. Additional VRAM is needed for KV-cache (18432 bytes per token) and activations (~0.20 GB).
What is the best GPU for Gemma 1.1 2B?
The top recommended GPU for Gemma 1.1 2B is the RTX 3080 using BF16 precision. It achieves approximately 738.7 tokens/sec at an estimated cost of $133/month ($0.07/M tokens). Score: 100/100.
How much does Gemma 1.1 2B inference cost?
Gemma 1.1 2B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.