gemma-4-31B

31.3B parameters, images and text in, text out, 256K tokens of context. 13 providers serve it from $0.10 per million input tokens.

Verified 2026-10-25 Rank #161 in LLMs · score 91.8 method v1 Sources 4 Downloads 30d 227.4k · #240 of 619 tracked

Can I run it?19GB at INT4Estimatefits a 24 GB cardmethodCommunity: Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap) →

What does it cost?$0.10/1M incheapest of 12CoreWeavefp42026-10-24

Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24

Do people use it?227.4kdownloads, 30 days#240 of 619 we track · top 39%+5 likes, downloads −39% this week575 likesHugging Face2026-10-24

Worth reading

Picked by rule from 41 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Most discussed · 868 HN pts

Gemma 4 on iPhone

apps.apple.com 2026-04-05 868 HN pts · 234 comments about the gemma 4 family family

Latest · 3 months ago

Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong

Cactus Hybrid introduces on-device models that score every answer with a confidence between 0 and 1 to decide when to hand off to a bigger model.

Weights on the meta device crash the confidence read because probes score generations outside the module forward path.
The probe is a patch you compile into the llama.cpp engine rather than a standalone library component.

github.com 2026-07-22 191 HN pts · 44 comments 714 words about the gemma 4 family family

25 best of 41 tracked

The 3 picks above, plus these 22. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

CodeShow HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Macgithub.com · 2026-07-29
ArticleGemma 4 12B: A unified, encoder-free multimodal modelblog.google · 2026-06-03 · official
ArticleRunning Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPUneomindlabs.com · 2026-07-15
ArticleGemma 4 QAT models: Optimizing compression for mobile and laptop efficiencyblog.google · 2026-06-05 · 406 HN pts · official
ArticleAccelerating Gemma 4: faster inference with multi-token prediction draftersblog.google · 2026-05-05 · 687 HN pts · official
ArticleGoogle releases Gemma 4 open modelsdeepmind.google · 2026-04-02 · 1,812 HN pts · official
CodeGemma 4 E2B inference in 700 lines of Cgithub.com · 2026-08-27 · 18 HN pts
ArticleFable 5 pushed Gemma 4 to 255 tok/s on WebGPUxcancel.com · 2026-06-18 · 48 HN pts
ArticleGoogle Gemma 4 Runs Natively on iPhone with Full Offline AI Inferencegizmoweek.com · 2026-04-15 · 303 HN pts
CodeApril 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac minigist.github.com · 2026-04-03
ArticleShow HN: Determinstic LLM inference for lowest price Gemma 4, with Windows XPtokendelivery.ai · 2026-09-12 · 9 HN pts
ArticleI ran Gemma 4 as a local model in Codex CLIblog.danielvaughan.com · 2026-04-12
ArticleRunning Gemma 4 locally with LM Studio's new headless CLI and Claude Codeai.georgeliu.com · 2026-04-05
ArticleGemma 4 on Cerebras - The Fastest Inference Is Now Multimodalcerebras.ai · 2026-06-30
CodeShow HN: Gemma 4 Multimodal Fine-Tuner for Apple Silicongithub.com · 2026-04-07
ArticleShow HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)teamchong.github.io · 2026-04-19
CodeShow HN: Local privacy-first Microsoft Recall alternative with Gemma 4github.com · 2026-07-04
ArticleGemma 4: Byte for byte, the most capable open modelsblog.google · 2026-04-02 · official
ArticleA Visual Guide to Gemma 4 12Bnewsletter.maartengrootendorst.com · 2026-06-03
CodeShow HN: Local LLM code-generation with Gemma 4 e2B via JSON AST to Clojuregithub.com · 2026-05-19
ArticleShow HN: Running Gemma-4 26B at 124 tokens/SEC on a CPU, no GPUapeg.dev · 2026-06-30
ArticleShow HN: I made a Gemma 4 Mac app that names screenshots with local AIsnapname.app · 2026-05-31

Show all 22

Where to run it

Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.

Prices for the same weights vary 8×

12 providers with a live price, from $0.10 to $0.75 per million input tokens; the median is $0.14. One dot per provider, cheapest in teal. 1 free-tier row not drawn.

#	Cheapest 5	In /1M	Out /1M	Context	Quant	Seen
1	CoreWeave	$0.10	$0.34	256K	fp4	Oct 24
2	Venice	$0.12	$0.36	250K	fp4	Oct 24
3	Chutes	$0.12	$0.37	128K	fp4	Oct 24
4	DeepInfra	$0.14	$0.51	256K	fp8	Oct 24
5	Crusoe	$0.14	$0.40	256K	bf16	Oct 24

All 13 providers →

Where it's used

Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.

Widely served (13 API providers); 45 quantized builds for local use; a big base for builders (107 fine-tunes, adapters and merges).

As a service13Chutes, CoreWeave, Crusoe, DeepInfra +9
On own hardware45quantized builds
Built on10798 fine-tunes · 6 adapters · 3 merges
In apps14Hugging Face Spaces

Will it fit?

Weights only, an estimate: leave room for the KV cache. Method

Fits a 64 GB Mac (unified memory) at INT4

About 19 GB at INT4, 38 GB at FP8, 75 GB at BF16: weights only, so leave room for the KV cache.

Estimate params × bytes per param × 1.2 · how we estimate

The story so far

Weights, every dated article, and repo commits on one rail.

10 dated articles and 6 repo commits so far

Teal is the weights (2026-03-12), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.

What people built on it

152 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

152 derivatives on the Hub, most of them fine-tunes

From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.

GGUF mradermacher/gemma-4-31B-i1-GGUF for llama.cpp, Ollama, LM Studio 66.5k downloads MLX majentik/gemma-4-31B-TurboQuant-MLX-4bit for Apple silicon 2.6k downloads INT4 lokeshe09/gemma-4-31B-it-INT4-W4A16 for vLLM, SGLang 1.1k downloads

All variants →

Reference

Everything else, folded: the full tables, every source.

Benchmarks

15 rows

Benchmarks 15 rows

measured third-party leaderboard rowauthor-reported number from the model card or eval files (15)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.

Benchmark	Value	Setting / notes	Reported by	Date
author-reported AIME 2026 · Reason through hard problems	89.2% percent	Gemma 4 31B	model author	2026-10-07
author-reported BBEH · Reason through hard problems	74.4% percent	Gemma 4 31B	model author	2026-10-07
author-reported Codeforces · Write code with agents	2150 elo	Gemma 4 31B	model author	2026-10-07
author-reported GPQA Diamond · Reason through hard problems	84.3% percent	Gemma 4 31B	model author	2026-10-07
author-reported HLE with search	26.5% percent	Gemma 4 31B	model author	2026-10-07
author-reported Humanity's Last Exam · Reason through hard problems	19.5% percent	Gemma 4 31B	model author	2026-10-07
author-reported LiveCodeBench · Write code with agents	80.0% percent	Gemma 4 31B	model author	2026-10-07
author-reported MMLU-Pro · Reason through hard problems	85.2% percent	Gemma 4 31B	model author	2026-10-07
author-reported MMMLU · Work across languages	88.4% percent	Gemma 4 31B	model author	2026-10-07
author-reported MMMU-Pro · Understand images and video	76.9% percent	Gemma 4 31B	model author	2026-10-07
author-reported MRCR · Read long documents	66.4% percent	Gemma 4 31B	model author	2026-10-07
author-reported MathVision · Understand images and video	85.6% percent	Gemma 4 31B	model author	2026-10-07
author-reported MedXPertQA MM	61.3% percent	Gemma 4 31B	model author	2026-10-07
author-reported OmniDocBench · Extract text from documents	0.13 other	Gemma 4 31B	model author	2026-10-07
author-reported tau-bench · Call tools and APIs	76.9% percent	Gemma 4 31B	model author	2026-10-07

What the card says

2 cited sentences

Summary generated, cited

Gemma 4 31B is a dense, multimodal model from Google DeepMind designed for image-text-to-text tasks.^[1]^[2] The model contains 32.7B parameters and supports a context window of up to 256K tokens.^[3]^[4]

“Gemma 4 models are multimodal, handling text and image input”
pipeline tag
parameters human
“context window of up to 256K tokens”

Generated 2026-10-07 15:01 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.

Use-case evidence

7 use cases

What it is good at 7 use cases

Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.

Facts

21 fields

Listed in LLMs

Facts

gemma-4-31B has 31.3B parameters. (safetensors metadata, observed 2026-10-24)
Context length is 262,144 tokens (256K). (config.json max_position_embeddings, observed 2026-10-24)
License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
Created 2026-03-12, last modified 2026-07-15. (HF API, observed 2026-10-24)

Pipeline tag	image-text-to-text
Library	transformers
Architectures	Gemma4ForConditionalGeneration
Model type	gemma4
Dtype	bfloat16
Params by dtype	BF16: 31,273,088,876
Size band	L
MoE	no
Context length	262,144 (config.json max_position_embeddings)
Papers	arXiv:2607.02770
License	Apache 2.0 (apache-2.0)
Hub snapshot	2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · Gemma4ForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Gemma4ForConditionalGeneration · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed

vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for gemma-4-31B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	75 GB · Single high-end GPU (<80 GB)
FP8 (1 byte/param)	38 GB · Single high-end GPU (<80 GB)
INT4 (0.5 bytes/param)	19 GB · Single GPU (<24 GB)

Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.

All variants

40 variants

Lineage

Original model Family: google/gemma-4 152 derivatives on the Hub

quantized: 45finetune: 98merge: 3adapter: 6

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
mradermacher/gemma-4-31B-i1-GGUF	quantized	GGUF	—	—	apache-2.0	mradermacher	8	66.5k
Mungert/gemma-4-31B-it-GGUF	quantized	GGUF	—	—	apache-2.0	Mungert	2	52.1k
mradermacher/gemma-4-31B-GGUF	quantized	GGUF	—	—	apache-2.0	mradermacher	8	38.6k
unsloth/gemma-4-31B	finetune	—	32.7B	L	apache-2.0	unsloth	20	15.9k
ggml-org/gemma-4-31B-GGUF	quantized	GGUF	—	—	apache-2.0	ggml-org	3	7.2k
tianrui6641/gemma-4-31b-gguf-mxfp4	quantized	gguf	—	—	apache-2.0	tianrui6641	1	4.2k
majentik/gemma-4-31B-RotorQuant-GGUF-IQ4_XS	quantized	GGUF	—	—	apache-2.0	majentik	0	4.2k
RedHatAI/gemma-4-31B-it	finetune	—	31.3B	L	apache-2.0	RedHatAI	0	3.4k
majentik/gemma-4-31B-TurboQuant-MLX-4bit	quantized	MLX	31.3B	L	apache-2.0	majentik	2	2.6k
thoughtworks/Gemma-4-31B-Eagle3	finetune	—	649M	S	gemma	thoughtworks	6	2.2k
majentik/gemma-4-31B-TurboQuant-MLX-8bit	quantized	MLX	31.3B	L	apache-2.0	majentik	1	2.2k
cloudbjorn/gemma-4-31B-Opus-4.6-Reasoning-GGUF	quantized	GGUF	—	—	apache-2.0	cloudbjorn	3	1.9k
xlr8harder/aria-gemma4-31b-v1	finetune	—	3.91B	M	apache-2.0	xlr8harder	1	1.7k
majentik/gemma-4-31B-RotorQuant-GGUF-Q2_K	quantized	GGUF	—	—	apache-2.0	majentik	0	1.6k
majentik/gemma-4-31B-TurboQuant-MLX-2bit	quantized	MLX	31.3B	L	apache-2.0	majentik	1	1.5k
ipsarkar/gemma-4-31B-GGUF	quantized	GGUF	—	—	apache-2.0	ipsarkar	0	1.6k
majentik/gemma-4-31B-RotorQuant-GGUF-Q4_K_M	quantized	GGUF	—	—	apache-2.0	majentik	0	1.5k
livadies/gemma-4-31B-Ghetto-NF4	quantized	-NF4	32.2B	L	gemma	livadies	8	1.1k
majentik/gemma-4-31B-RotorQuant-GGUF-Q5_K_M	quantized	GGUF	—	—	apache-2.0	majentik	0	1.4k
majentik/gemma-4-31B-RotorQuant-GGUF-Q3_K_M	quantized	GGUF	—	—	apache-2.0	majentik	0	1.3k
virtuous7373/Gemma-4-Harmonia-31B	merge	—	31.3B	L	—	virtuous7373	17	396
lokeshe09/gemma-4-31B-it-INT4-W4A16	quantized	INT4	31.5B	L	apache-2.0	lokeshe09	0	1.1k
Dev-Louislu/gemma-4-31B-Q4_K_M-GGUF	quantized	GGUF	—	—	apache-2.0	Dev-Louislu	0	1k
lokeshe09/gemma-4-31B-it-FP8-Dynamic	quantized	-FP8	31.3B	L	apache-2.0	lokeshe09	0	1k
majentik/gemma-4-31B-RotorQuant-GGUF-Q8_0	quantized	GGUF	—	—	apache-2.0	majentik	1	956
livadies/gemma-4-31B-Base-Ghetto-NF4	quantized	-NF4	32.2B	L	gemma	livadies	2	826
zeromodels/gemma-4-31b	finetune	—	—	—	apache-2.0	zeromodels	0	831
xlr8harder/aria-gemma4-31b-stage1-wildchat-v1	finetune	—	3.91B	M	apache-2.0	xlr8harder	1	780
JMingo/gemma-4-31B-it-GGUF	quantized	GGUF	—	—	apache-2.0	JMingo	0	730
gjdeboer/gemma-4-31B-mlx-fp16	finetune	mlx	30.7B	L	apache-2.0	gjdeboer	1	668
ark4004/gemma-4-31B-it-jh	finetune	—	31.3B	L	apache-2.0	ark4004	1	662
cyzero-kim/gemma-4-31B-Opus-4.6-Reasoning	finetune	—	31.3B	L	apache-2.0	cyzero-kim	2	516
OrobasVault/Vespera-Synapse-31B	merge	—	32.1B	L	apache-2.0	OrobasVault	4	375
noterat/forseti-31b	finetune	—	32.1B	L	apache-2.0	noterat	1	507
ipsarkar/gemma-4-31B-BF16-GGUF	quantized	-BF16	—	—	apache-2.0	ipsarkar	0	516
bugrabilge/Omni-31B-Turkish-Reasoning-Model	finetune	—	31.3B	L	gemma	bugrabilge	6	210
FusionCow/gemma-4-31B-Q3_K_M-GGUF	quantized	GGUF	—	—	apache-2.0	FusionCow	0	479
katiyardinesh/gemma-4-31B-it-custom	finetune	—	31.3B	L	apache-2.0	katiyardinesh	0	437
CosmicBee/gemma_4_finetune	quantized	GGUF	—	—	cc-by-4.0	CosmicBee	0	414
cloudbjorn/gemma-4-31B-Opus-4.6-Reasoning	finetune	—	31.3B	L	apache-2.0	cloudbjorn	1	337

Repository changelog

6 commits

Repository changelog 6 commits

Date	Commit	SHA
2026-07-15	Update README (#7)	5bbc2fb
2026-07-10	Add Technical Report	d77cb0b
2026-06-03	Update README.md	02e15e4
2026-06-02	Update README.md	1e58d60
2026-04-02	Upload tokenizer.json	5dc307e
2026-04-02	Preparing for release!	2d418d1

All providers

13 providers · 13 endpoints

Where to run 13 providers · 13 endpoints

Hosted endpoints observed for gemma-4-31B, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.00/M.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
Google AI Studio openrouter	google/gemma-4-31b-it	256K	unknown	$0.00	$0.00	—	—	yes	live	2026-10-24
CoreWeave openrouter	google/gemma-4-31b-it	256K	fp4	$0.10	$0.34	—	—	yes	live	2026-10-24
Venice openrouter	google/gemma-4-31b-it	250K	fp4	$0.12	$0.36	—	—	yes	live	2026-10-24
Chutes openrouter	google/gemma-4-31b-it	128K	fp4	$0.12	$0.37	—	—	yes	live	2026-10-24
DeepInfra deepinfra, openrouter	google/gemma-4-31B-it	256K	fp8	$0.14	$0.51	—	—	yes	live	2026-10-24
Crusoe openrouter	google/gemma-4-31b-it	256K	bf16	$0.14	$0.40	—	—	yes	live	2026-10-24
Friendli openrouter	google/gemma-4-31b-it	256K	unknown	$0.14	$0.40	—	—	yes	live	2026-10-24
Novita openrouter	google/gemma-4-31b-it	256K	bf16	$0.14	$0.40	—	—	yes	live	2026-10-24
Parasail parasail, openrouter	google/gemma-4-31B	256K	fp8	$0.15	$0.40	—	—	yes	serverless	2026-10-24
Io Net openrouter	google/gemma-4-31b-it	256K	unknown	$0.36	$1.09	—	—	yes	live	2026-10-24
SambaNova openrouter	google/gemma-4-31b-it	128K	unknown	$0.38	$1.15	—	—	yes	live	2026-10-24
ModelRun openrouter	google/gemma-4-31b-it	256K	fp4	$0.75	$1.00	—	—	yes	live	2026-10-24
SiliconFlow openrouter	google/gemma-4-31b-it	256K	fp8	$0.75	$1.00	—	—	yes	live	2026-10-24

Articles and coverage

41 pieces

Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.

Official3

Gemma 4 QAT models: Optimizing compression for mobile and laptop efficiency

blog.google2026-06-05officialauthorityHN front pageabout the gemma 4 familyHN 406 pts · 130 comments714 words

Google released new Gemma 4 checkpoints optimized with Quantization-Aware Training to improve efficiency on edge devices and consumer GPUs. The E2B model achieves a 1GB memory footprint using a mobile-specialized schema that applies targeted 2-bit quantization to token generation layers. Developers can access GGUF formats ready for llama.cpp and MTP QAT checkpoints to preserve inference speedups while running locally.written, reviewed, cited

The mobile-specialized schema pre-calculates activation scaling settings during training to reduce workload on mobile chips.
Targeted 2-bit quantization compresses token generation parts while keeping core reasoning layers at higher precision.
Deploying only needed modalities allows the Gemma 4 E2B text-only model to require less than 1 GB of memory.

Accelerating Gemma 4: faster inference with multi-token prediction drafters

blog.google2026-05-05officialauthorityHN front pageabout the gemma 4 familyHN 687 pts · 330 comments796 words

Google released Multi-Token Prediction (MTP) drafters for the Gemma 4 family under the same open-source Apache 2.0 license as Gemma 4. These drafters deliver up to a 3x speedup for models like the 26B MoE and 31B Dense versions without quality degradation. Benchmarks on hardware such as the NVIDIA RTX PRO 6000 show that increasing batch sizes to 4 to 8 unlocks up to a ~2.2x speedup locally.written, reviewed, cited

The MTP drafter shares the target model's KV cache to avoid recalculating context the larger model has already processed.
For E2B and E4B edge models, an efficient clustering technique in the embedder accelerates generation where logit calculation is a bottleneck.
The 26B mixture-of-experts model presents unique routing challenges at a batch size of 1 on Apple Silicon.

Google releases Gemma 4 open models

deepmind.google2026-04-02officialauthorityHN front pageabout the gemma 4 familyHN 1,812 pts · 474 comments253 words

Analysis7

Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong

github.com2026-07-22authorityHN front pageabout the gemma 4 familyHN 191 pts · 44 comments714 words

Cactus Hybrid introduces on-device models that score every answer with a confidence between 0 and 1 to decide when to hand off to a bigger model. The Gemma 4 E2B Hybrid model matches Gemini 3.1 Flash-Lite performance by routing only 15–55% of queries to the cloud while running the rest locally. It is MIT-licensed and achieves a 0.770 AUROC on MMLU, with a probe trained on zero audio data yet reaching 0.79–0.88 AUROC on four audio benchmarks.written, reviewed, cited

Weights on the meta device crash the confidence read because probes score generations outside the module forward path.
The probe is a patch you compile into the llama.cpp engine rather than a standalone library component.
Transformers version 5.14 and above cause a segfault on this specific checkpoint.

Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)

blog.simbastack.com2026-05-21HN front pageHN 471 pts · 142 comments2,652 words

Gemma 4 E2B inference in 700 lines of C

github.com2026-08-27authorityabout the gemma 4 familyHN 18 pts · 0 comments722 words

Fable 5 pushed Gemma 4 to 255 tok/s on WebGPU

xcancel.com2026-06-18about the gemma 4 familyHN 48 pts · 22 comments

Gemma 4 on iPhone

apps.apple.com2026-04-05HN front pageabout the gemma 4 familyHN 868 pts · 234 comments

Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

gizmoweek.com2026-04-15HN front pageabout the gemma 4 familyHN 303 pts · 187 comments364 words

Show HN: Determinstic LLM inference for lowest price Gemma 4, with Windows XP

tokendelivery.ai2026-09-12about the gemma 4 familyHN 9 pts · 1 comments

All coverage tracked for this model (41) — append-only, nothing is ever removed

Title	Source	Published	First seen	Signals
Gemma 4 Technical Report	arxiv.org	—	2026-10-07	exa
Gemma 4 31B Models - Intelligence, Performance & Price Comparison \| Artificial Analysis	artificialanalysis.ai	—	2026-10-07	exa
Gemma 4 Architecture: How 31B Beats 400B Models	kriraai.com	—	2026-10-07	exa
Gemma 4 31B Explained: Architecture and GPU Needs \| Vucense	vucense.com	—	2026-10-07	exa
Show HN: Determinstic LLM inference for lowest price Gemma 4, with Windows XP	tokendelivery.ai	2026-09-12	2026-10-07	hn
Gemma 4 E2B inference in 700 lines of C	github.com	2026-08-27	2026-10-07	hn
Reachpad now includes free Gemma 4 31B and Gemini 3.6 Flash	reachpad.dev	2026-08-13	2026-10-07	hn
Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac	github.com	2026-07-29	2026-10-07	hn
Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong	github.com	2026-07-22	2026-10-07	hn
Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU	neomindlabs.com	2026-07-15	2026-10-07	hn
Show HN: Local privacy-first Microsoft Recall alternative with Gemma 4	github.com	2026-07-04	2026-10-07	hn
Show HN: Running Gemma-4 26B at 124 tokens/SEC on a CPU, no GPU	apeg.dev	2026-06-30	2026-10-07	hn
Gemma 4 on Cerebras - The Fastest Inference Is Now Multimodal	cerebras.ai	2026-06-30	2026-10-07	hn
Fable 5 pushed Gemma 4 to 255 tok/s on WebGPU	xcancel.com	2026-06-18	2026-10-07	hn
Gemma-4-31B at 256K context on a $1,400 AMD GPU – measured, with patches	github.com	2026-06-10	2026-10-07	hn
Gemma 4 QAT models: Optimizing compression for mobile and laptop efficiency	blog.google official	2026-06-05	2026-10-07	hn
Google's new Gemma 4 12B model is designed to run on any laptop with 16GB of RAM	arstechnica.com	2026-06-03	2026-10-07	hn
A Visual Guide to Gemma 4 12B	newsletter.maartengrootendorst.com	2026-06-03	2026-10-07	hn
Gemma 4 12B: A unified, encoder-free multimodal model	blog.google official	2026-06-03	2026-10-07	hn
Show HN: I made a Gemma 4 Mac app that names screenshots with local AI	snapname.app	2026-05-31	2026-10-07	hn
Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)	blog.simbastack.com	2026-05-21	2026-10-07	hn
Show HN: Local LLM code-generation with Gemma 4 e2B via JSON AST to Clojure	github.com	2026-05-19	2026-10-07	hn
Accelerating Gemma 4: faster inference with multi-token prediction drafters	blog.google official	2026-05-05	2026-10-07	hn
Running Gemma 4 31B on Mac with Ollama	sammyrulez.github.io	2026-04-27	2026-10-07	hn
Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)	teamchong.github.io	2026-04-19	2026-10-07	hn
Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference	gizmoweek.com	2026-04-15	2026-10-07	hn
Show HN: I benchmarked Gemma 4 E2B – the 2B model beat the 12B on multi-turn	aiexplr.com	2026-04-13	2026-10-07	hn
I ran Gemma 4 as a local model in Codex CLI	blog.danielvaughan.com	2026-04-12	2026-10-07	hn
A Visual Guide to Gemma 4	newsletter.maartengrootendorst.com	2026-04-09	2026-10-07	hn
Show HN: Gemma 4 Multimodal Fine-Tuner for Apple Silicon	github.com	2026-04-07	2026-10-07	hn
Gemma 4 31B GGUF quants ranked by KL divergence	localbench.substack.com	2026-04-07	2026-10-07	hn
Gemma 4 on iPhone	apps.apple.com	2026-04-05	2026-10-07	hn
Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code	ai.georgeliu.com	2026-04-05	2026-10-07	hn
Gemma 4: Google DeepMind's Most Intelligent Open Models \| AI \| Tobias Weiss	tobias-weiss.org	2026-04-04	2026-10-07	exa
Gemma 4 Review: Apache-2.0 Open AI, 89.2% on AIME 2026 \| Nerd Level Tech	nerdleveltech.com	2026-04-04	2026-10-07	exa
April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini	gist.github.com	2026-04-03	2026-10-07	hn
Gemma 4 Deep Dive: Architecture, Benchmarks, and Impact — Swfte AI	swfte.com	2026-04-03	2026-10-07	exa
Google releases Gemma 4 open models	deepmind.google official	2026-04-02	2026-10-07	hn
Gemma 4: Byte for byte, the most capable open models	blog.google official	2026-04-02	2026-10-07	hn
Gemma 4 Architecture and Benchmark Notes \| Sebastian Raschka, PhD	sebastianraschka.com	2026-04-02	2026-10-07	exa
Gemma 4 31B: 262K Context & GPQA Diamond Score \| HokAI	hokai.io	2026-04-02	2026-10-07	exa

Papers

1 paper

Papers 1

arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).

Gemma 4 Technical Report this model

Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320 · 2026-07-02 · PDF · HF paper page (85 upvotes)

Similar models

3 models

Similar models

Qwen3.8-27B · 27.8B
same size band (L), same task (image-text-to-text), more providers, permissive license
Qwen3.6-27B · 27.8B
same size band (L), same task (image-text-to-text), more providers, permissive license
Muse-Glimmer-30B · 29.8B
same size band (L), same task (image-text-to-text), more providers, permissive license

Sources

4 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:34 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:01 UTC · Last verified 2026-10-25

Follow gemma-4-31B

Watch this model

/feeds/models/google--gemma-4-31B.xml(RSS 2.0) · every change to gemma-4-31B
/feeds/families/google--gemma-4.xml(RSS 2.0) · every change across the gemma-4 family

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.