Models / Gemma 4 31B

Gemma 4 31B

enthusiast
HuggingFace → HuggingBay → Google → Find for my hardware

30.7B dense (no MoE) with hybrid attention - a 1024-token sliding window interleaved with full global attention across 60 layers - for a real 256K context. Multimodal (text + image). Apache 2.0.

The dense Gemma 4 sibling: more per-token quality than the 26B A4B MoE, at the cost of full 30.7B decode.

  • Q4_K_M (~18.3GB weights, ~20GB runtime) fits a 24GB 4090.
  • QAT (~19GB) is near-lossless at the same size.
  • Q8_0 (~33GB) needs 2x 3090 or 48GB.
  • BF16 (~61GB) needs a big rig.

AI-generated content marks

The provider reports that this model does not add embedded watermarks or provenance metadata to generated output.

Provider transparency docs →

coding reasoning writing chat general vision
Parameters
30.7B
Context
256k
License
apache 2.0
Developer
Google
Origin
🇺🇸 USA
Released
Apr 2026

Scores

Coding
86
Reasoning
89
General
85

Score per dollar

1063 pts per $/M input

general_score (85) divided by cheapest input price ($0.08/M). Higher is better value. See live pricing.

Related models

Gemma 4 26B A4B
25.2B 3.8B active enthusiast 15GB min RAM $0.04/M in Apr 30, 2026
Gemma 3 270M
270M edge 1GB min RAM Aug 14, 2025
Gemma 3n E2B
2.0B edge 6GB min RAM Jun 26, 2025
Gemma 3n E4B
4.0B edge 8GB min RAM Jun 26, 2025
Gemma 4 12B
12.0B consumer 7GB min RAM Jun 1, 2025
Gemma 3 12B
12.2B consumer 8GB min RAM $0.05/M in Feb 27, 2025
Gemma 3 1B
1.0B edge 1GB min RAM Feb 27, 2025
Gemma 3 27B
27.2B consumer 17GB min RAM $0.08/M in Feb 27, 2025
Gemma 3 4B
4.3B edge 3GB min RAM $0.05/M in Feb 27, 2025

Guides covering Gemma 4 31B

DGX Spark benchmarks: which local model wins in 2026 Aug 19, 2026 Open-weights models cost less: a 2026 pricing guide Jul 6, 2026

Save your hardware and every model page answers the real question: will it run on your machine, and how fast?

Join free - save your rig →

Run it locally

Per-quant memory needs and a static "can you run it?" reference - no rig entry required

QAT
18.0GB 19.0GB min 22.0GB rec
Quantization-aware training - near-lossless at Q4 size
Q4_K_M
18.3GB 20.0GB min 22.0GB rec
Balanced - the usual local sweet spot
NVFP4
16.0GB 20.0GB min 22.0GB rec
NVIDIA FP4 - Blackwell or Apple MLX, near-lossless
Q8_0
32.6GB 34.0GB min 38.0GB rec
Near-lossless
BF16
61.4GB 63.0GB min 66.0GB rec
Full quality, largest

The reference hardware

Schematic of the NVIDIA Jetson Orin NX 16GB reference rig - 16GB unified memory, 102 GB/s aggregate bandwidth
Schematic of the Single GTX 1080 Ti (11GB) reference rig - 11GB VRAM, 484 GB/s aggregate bandwidth
Schematic of the 4x H100 80GB (320GB) reference rig - 320GB VRAM, 13400 GB/s aggregate bandwidth
Schematic of the 4x RTX 5090 (128GB) reference rig - 128GB VRAM, 7168 GB/s aggregate bandwidth
Schematic of the NVIDIA DGX Station 748GB reference rig - 748GB unified memory, 8000 GB/s aggregate bandwidth
Schematic of the 8x RTX 3090 rack (192GB) reference rig - 192GB VRAM, 7489 GB/s aggregate bandwidth
Schematic of the AMD Instinct MI300X (192GB) reference rig - 192GB VRAM, 5324 GB/s aggregate bandwidth
Schematic of the 2x RTX 5090 (64GB) reference rig - 64GB VRAM, 3584 GB/s aggregate bandwidth
Schematic of the 4x RTX 4090 (96GB) reference rig - 96GB VRAM, 4032 GB/s aggregate bandwidth
Schematic of the Single RTX 5090 (32GB) reference rig - 32GB VRAM, 1792 GB/s aggregate bandwidth
Schematic of the RTX PRO 6000 Blackwell (96GB) reference rig - 96GB VRAM, 1792 GB/s aggregate bandwidth
Schematic of the 2x RTX 3090 (48GB) reference rig - 48GB VRAM, 1872 GB/s aggregate bandwidth
Schematic of the Mac Studio M4 Ultra 192GB reference rig - 192GB unified memory, 1092 GB/s aggregate bandwidth
Schematic of the Mac Studio M4 Ultra 512GB reference rig - 512GB unified memory, 1092 GB/s aggregate bandwidth
Schematic of the Single RTX 4090 (24GB) reference rig - 24GB VRAM, 1008 GB/s aggregate bandwidth
Schematic of the MacBook Pro M5 Max 128GB reference rig - 128GB unified memory, 614 GB/s aggregate bandwidth
Schematic of the Dual EPYC 9004 + 768GB DDR5-4800 reference rig - 768GB unified memory, 460 GB/s aggregate bandwidth
Schematic of the DGX Spark 128GB unified reference rig - 128GB unified memory, 273 GB/s aggregate bandwidth
Schematic of the Ryzen AI Max+ 395 128GB reference rig - 128GB unified memory, 256 GB/s aggregate bandwidth
Schematic of the Jetson AGX Orin 64GB reference rig - 64GB unified memory, 204 GB/s aggregate bandwidth
Schematic of the Epyc + 512GB DDR4-3200 + 2x RTX 3090 reference rig - 560GB unified memory, 204 GB/s aggregate bandwidth
Schematic of the Epyc + 512GB DDR4-2400 + 2x RTX 3090 reference rig - 560GB unified memory, 153 GB/s aggregate bandwidth

22 reference configs, drawn in-house. Scroll for more.

Can you run it? - reference rigs

Rig QAT Q4_K_M NVFP4 Q8_0 BF16
NVIDIA Jetson Orin NX 16GB no -> cloud no -> cloud no -> cloud no -> cloud no -> cloud
Single GTX 1080 Ti (11GB) no -> cloud no -> cloud no -> cloud no -> cloud no -> cloud
4x H100 80GB (320GB) fast 409.4t/s fast 402.7t/s no -> cloud fast 226.1t/s fast 120.0t/s
4x RTX 5090 (128GB) fast 219.0t/s fast 215.4t/s fast 246.4t/s fast 120.9t/s fast 64.2t/s
NVIDIA DGX Station 748GB fast 244.4t/s fast 240.4t/s no -> cloud fast 135.0t/s fast 71.7t/s
8x RTX 3090 rack (192GB) fast 228.8t/s fast 225.1t/s no -> cloud fast 126.4t/s fast 67.1t/s
AMD Instinct MI300X (192GB) fast 162.7t/s fast 160.0t/s no -> cloud fast 89.8t/s fast 47.7t/s
2x RTX 5090 (64GB) fast 109.5t/s fast 107.7t/s fast 123.2t/s fast 60.5t/s tight
4x RTX 4090 (96GB) fast 123.2t/s fast 121.2t/s no -> cloud fast 68.0t/s fast 36.1t/s
Single RTX 5090 (32GB) fast 54.8t/s fast 53.9t/s fast 61.6t/s offload no -> cloud
RTX PRO 6000 Blackwell (96GB) fast 54.8t/s fast 53.9t/s fast 61.6t/s fast 30.2t/s ok 16.1t/s
2x RTX 3090 (48GB) fast 57.2t/s fast 56.3t/s no -> cloud fast 31.6t/s offload
Mac Studio M4 Ultra 192GB fast 36.4t/s fast 35.8t/s fast 40.9t/s fast 20.1t/s ok 10.7t/s
Mac Studio M4 Ultra 512GB fast 36.4t/s fast 35.8t/s fast 40.9t/s fast 20.1t/s ok 10.7t/s
Single RTX 4090 (24GB) fast 30.8t/s fast 30.3t/s no -> cloud offload no -> cloud
MacBook Pro M5 Max 128GB fast 20.5t/s fast 20.1t/s fast 23.0t/s ok 11.3t/s slow 6.0t/s
Dual EPYC 9004 + 768GB DDR5-4800 ok 14.1t/s ok 13.9t/s no -> cloud slow 7.8t/s slow 4.1t/s
DGX Spark 128GB unified ok 8.3t/s ok 8.2t/s ok 9.4t/s slow 4.6t/s slow 2.5t/s
Ryzen AI Max+ 395 128GB slow 7.8t/s slow 7.7t/s no -> cloud slow 4.3t/s slow 2.3t/s
Jetson AGX Orin 64GB slow 6.3t/s slow 6.2t/s no -> cloud slow 3.5t/s tight
Epyc + 512GB DDR4-3200 + 2x RTX 3090 slow 6.3t/s slow 6.2t/s no -> cloud slow 3.5t/s slow 1.8t/s
Epyc + 512GB DDR4-2400 + 2x RTX 3090 slow 4.7t/s slow 4.6t/s no -> cloud slow 2.6t/s slow 1.4t/s

Fit tiers use the same will-it-run logic as the rig finder. For comfortable fits, the badge reflects decode speed: fast >=20 t/s, ok 8-20 t/s, slow <8 t/s. t/s is a bandwidth estimate, not a measured benchmark.

Download options

QAT official -1% vs fp16
18.0GB dl 19.0GB min 22.0GB rec
REC RAM vs largest quant
Q4_K_M official -5% vs fp16
18.3GB dl 20.0GB min 22.0GB rec
REC RAM vs largest quant
NVFP4 official -1% vs fp16
16.0GB dl 20.0GB min 22.0GB rec
REC RAM vs largest quant
NVFP4 - NVIDIA Blackwell via vLLM or Apple Silicon via MLX (ollama run gemma4:31b-nvfp4). Not supported on Ada/Ampere/Hopper/AMD.
Q8_0 official -1% vs fp16
32.6GB dl 34.0GB min 38.0GB rec
REC RAM vs largest quant
BF16 official
61.4GB dl 63.0GB min 66.0GB rec
REC RAM vs largest quant
GGUF on HF →

Or run it in the cloud

Live per-provider pricing, throughput and uptime - refreshed about 8 hours ago via OpenRouter. Click a column to sort.

some pricing may be stale - last verified 2026-09-29

Provider Type Input $/M Output $/M Cache $/M Tok/s Latency Uptime Value
Crusoe
API 0.14 0.40 0.140 - - 100.00% best uptime
SambaNova
API 0.38 1.15 0.050 - - 100.00%
Together AI stale
API 0.39 0.97 - - - -
ModelRun
API 0.75 1.00 0.750 - - 99.94%
Reka
API 0.08 0.30 0.050 - - 99.88% cheapest
Friendli
API 0.14 0.40 0.050 - - 99.87%
Parasail
API 0.15 0.40 0.060 - - 99.83%
SiliconFlow
API 0.75 1.00 0.250 - - 99.75%
CoreWeave
API 0.10 0.34 0.100 - - 99.43%
Io Net
API 0.38 1.15 0.190 - - 99.09%
Chutes
API 0.12 0.37 0.012 - - 98.68%
Venice
API 0.12 0.36 0.090 - - 98.57%
DeepInfra risky
API 0.27 0.76 0.050 - - 94.83%
Novita avoid
API 0.14 0.40 0.050 - - 69.46%

Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.

Detailed API pricing page + JSON endpoint →

See who runs Google in production →

PRICE HISTORY

Inference cost over time

Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.

Loading price history...