Up to date
google Apache 2.0 out 6 months ago
470M parameters, several kinds of input and output, 256K tokens of context.
Verified 2026-10-25 Rank #320 in LLMs · score 82.4 method v1 Sources 3 Downloads 30d 293.3k · #221 of 619 tracked
Picked by rule from 27 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 23. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
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.
No API provider serves it, so its downloads are people running it themselves: 11 quantized builds and 7 Spaces.
Top Spaces running it: build-small-hackathon/read_the_room ♥ 4 · shuarya2011/Assistant ♥ 2
Weights only, an estimate: leave room for the KV cache. Method
About 0.3 GB at INT4, 0.6 GB at FP8, 1.1 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2026-04-23), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
18 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
| 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 |
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.
Listed in LLMs
| Pipeline tag | any-to-any |
|---|---|
| Library | transformers |
| Architectures | Gemma4AssistantForCausalLM |
| Model type | gemma4_assistant |
| Dtype | bfloat16 |
| Params by dtype | BF16: 469,518,596 |
| Size band | S |
| 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 |
vLLM: not in registry · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: not in registry · 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.
Weights-only memory for gemma-4-31B-it-assistant: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 1.1 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 0.6 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.3 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
finetune: 7quantized: 11
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| google/gemma-4-31B-it-qat-q4_0-unquantized-assistant | finetune | q4_0 | 470M | S | apache-2.0 | 32 | 216.9k | |
| AtomicChat/gemma-4-31B-it-assistant-GGUF | quantized | GGUF | — | — | apache-2.0 | AtomicChat | 22 | 34.4k |
| mlx-community/gemma-4-31B-it-assistant-bf16 | finetune | -bf16 | 470M | S | gemma | mlx-community | 21 | 23.4k |
| Radamanthys11/Gemma-4-31B-it-assistant-GGUF | quantized | GGUF | — | — | gemma | Radamanthys11 | 17 | 22.2k |
| NotMe404/gemma-4-31b-it-assistant-mtp-gguf | quantized | gguf | — | — | — | NotMe404 | 9 | 14.7k |
| cafkafk/gemma-4-31B-it-assistant-GGUF-noimatrix | quantized | GGUF | — | — | gemma | cafkafk | 8 | 5.6k |
| bahadirakdemir/gemma-4-31B-it-assistant-fp8 | quantized | -fp8 | 470M | S | apache-2.0 | bahadirakdemir | 2 | 2k |
| Phil2Sat/gemma-4-31B-it-assistant-GGUF | quantized | GGUF | — | — | apache-2.0 | Phil2Sat | 0 | 1.5k |
| tiyuvta/gemma-4-31B-it-assistant-MTP-GGUF | quantized | GGUF | — | — | apache-2.0 | tiyuvta | 1 | 917 |
| yujiepan/gemma-4-assistant-tiny-random | finetune | — | 2.12M | S | — | yujiepan | 0 | 475 |
| tiny-random/gemma-4-assistant | finetune | — | 2.12M | S | — | tiny-random | 0 | 385 |
| NeoRoth/gemma-4-31b-it-assistant-mlx | finetune | mlx | 470M | S | gemma | NeoRoth | 0 | 363 |
| Nabhos/gemma-4-31B-it-assistant-AWQ-4bit | quantized | AWQ | 470M | S | — | Nabhos | 0 | 248 |
| BarraHome/gemma-4-31B-it-assistant-FP8-dynamic | quantized | -FP8 | 470M | S | apache-2.0 | BarraHome | 0 | 187 |
| BarraHome/gemma-4-31B-it-assistant-FP8-block | quantized | -FP8 | 470M | S | apache-2.0 | BarraHome | 1 | 88 |
| edp1096/gemma-4-31B-it-assistant-exl3 | quantized | exl3 | 151M | S | apache-2.0 | edp1096 | 1 | 63 |
| keptn/gemma4-31b-heretic-ara-w4a8 | finetune | — | — | — | apache-2.0 | keptn | 0 | 67 |
| Terom/gemma-4-31B-it-qat-q4_0-unquantized-assistant | finetune | q4_0 | 470M | S | apache-2.0 | Terom | 0 | 48 |
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.
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).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:38 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:08 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
