Gemma 4 31B
Parameters
30.7B
Context Length
256K
Modality
Multimodal
Auxiliary Parameters
450M
Architecture
Dense
KV Cache Rate
960 KB/tok
License
Apache 2.0
Release Date
2 Apr 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.16 · Output: $0.47
Hardware & System Requirements
Precision
Context
Workload Memory: 24.30 GB
INT4 · 8K context
Base Weights: 14.30 GB
KV Cache: 7.50 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA A40 48GB
24.3 / 43.2 GB usable
2x RTX 4090 24GB
24.3 / 43.2 GB usable · TP 2
Apple M3 Pro 36GB
24.3 / 27.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
Rank
#191
| Benchmark | Score | Rank |
|---|---|---|
Professional Knowledge | 0.852 | 11 |
Graduate-Level QA | 0.843 | 47 |
Reasoning | 0.68 | 62 |
Data Analysis | 0.53 | 62 |
Coding | 0.49 | 63 |
General | 0.42 | 65 |
LiveBench Average | 0.42 | 65 |
General Text | 1452 | 67 |
Agent Arena | -23.7 | 68 |
Web Development | 1370 | 94 |
Agentic Index | auto 0.04 | 102 |
Coding Index | 0.33 | 116 |
Intelligence Index | auto 0.04 | 332 |
Rankings
Overall Rank
#191
Coding Rank
#140
About Gemma 4 31B
Gemma 4 31B is the flagship dense model with 30.7B parameters and 256K context window, delivering frontier intelligence for workstations and consumer GPUs. Supports text and image input with state-of-the-art performance on coding, reasoning, and multimodal understanding. Features configurable thinking mode and native function calling for advanced agentic workflows and IDE integration.
Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
32
Key-Value Heads
16
Attention Head Dimension
256
Position Embedding
ROPE
RoPE Theta
1,000,000
Sliding Window Attention
Yes
Sliding Window Size
1,024
Sliding Window Ratio
83.3%
Normalization
RMS Normalization
Activation Function
GELU
Dimensions
Base Precision
BF16
Auxiliary Parameters
450M
Hidden Dimension Size
5,376
Number of Layers
60
FFN Intermediate Size (Dense)
21,504
Tokenizer
Vocabulary Size
262,144
About Gemma 4
Gemma 4 is Google DeepMind's most advanced open model family, built from Gemini 3 research and technology. Featuring both Dense and Mixture-of-Experts (MoE) architectures, these multimodal models handle text, images, and audio (on smaller variants), with context windows up to 256K tokens. Designed for frontier-level performance across reasoning, coding, and agentic workflows, Gemma 4 delivers unprecedented intelligence-per-parameter from mobile devices to enterprise servers. Released under Apache 2.0 license.