- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- Family
- Gemma 4
- Task
- vision-language
- Hugging Face
- google/gemma-4-31B-it
- OpenRouter
- google/gemma-4-31b-it
- Also known as
- gemma-4-31b-it, gemma4 31b, gemma 31b
02Registry facts
- LicenceFACT
apache-2.0
- FreshRetrieved 19 Sep 2026
- ParametersFACT
31.3B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
9,072,622
- FreshRetrieved 19 Sep 2026
- LikesFACT
3,864
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
9072622
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · VeniceFACT
256000
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · CoreWeaveFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · DeepInfraFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
3864
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
apache-2.0
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
31273088876
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · VeniceFACT
0.3600
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · CoreWeaveFACT
0.3400
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · DeepInfraFACT
0.3400
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · VeniceFACT
0.1200
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · CoreWeaveFACT
0.1000
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · DeepInfraFACT
0.0900
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · vendorFACT
vendor
- AgeingRetrieved 19 Sep 2026
- available on platform · awsFACT
aws
Evidence not verified — the quoted phrase was not found in the fetched document.
- Evidence not verified
- last modifiedFACT
2026-07-20T16:42:18.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 31.3B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 62.55 GB | 81.81 GB |
| int8 | 31.27 GB | 45.84 GB |
| int4 | 15.64 GB | 27.86 GB |
| q4_k_mSized as 4-bit weights. Q4_K_M averages nearer 4.5 bits in practice, so read this as a floor. | 15.64 GB | 27.86 GB |
What this estimate assumes
- Weights: 31.3B parameters × 2 bytes per parameter (fp16) = 62.55 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.262 MB per token, from Qwen2.5-32B-Instruct (64 × 8 × 128).
- KV cache: 0.262 MB per token × 8,192 tokens of context × 4 concurrent requests = 8.59 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 10.67 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.09
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
0.33999999999999997
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| DeepInfra | 262,144 |
| CoreWeave | 262,144 |
| Venice | 256,000 |
| Chutes | 131,072 |
| DeepInfra | 262,144 |
| Crusoe | 262,144 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01Tier 2official vendor legal documentationVendor legal and technical documentation
google/gemma-4-31B-it · Hugging Face
https://huggingface.co/google/gemma-4-31B-it
AgeingRetrieved 19 Sep 2026sha256:8a2370f815101 record
- 02–10Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — google/gemma-4-31b-it
https://openrouter.ai/api/v1/models/google/gemma-4-31b-it/endpoints
Verification may be outdatedRetrieved 19 Sep 2026sha256:3db3e8fe9acc9 records · · · · · · · ·
- 11–17Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — google/gemma-4-31B-it
https://huggingface.co/api/models/google/gemma-4-31B-it
Verification may be outdatedRetrieved 19 Sep 2026sha256:fe5c5fc2862c7 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.