willitrun·ai

GoogleGoogle

DiffusionGemma 26B A4B

Frontier
huggingfaceHuggingFace
1.7MDownloads1.1KCurtidasJun 2026Publicado262K tokensContextoApache 2.0Licença68 BomQualidade

DiffusionGemma 26B A4B (25.799999237060547B parameters) requires approximately 22.4 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 4B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 26 GB of VRAM.

Comece agora

— copie e cole para rodar localmente

Copy-paste commands to run DiffusionGemma 26B A4B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \ --hf-repo "google/diffusiongemma-26B-A4B-it" \ --hf-file "diffusiongemma-26B-A4B-it-Q4_K_M.gguf" \ -c 4096 -ngl 99

Quick specs

Parameters25.8B (4B active)
Architecturemoe (MoE)
Context262K tokens
Modalitytext
Min RAM10.1 GB
Rec. RAM15.7 GB (Q4_K_M)
LicenseApache 2.0
FamilyGemma
✓ Vision✓ Chat✓ Reasoning

About this model

DiffusionGemma 26B A4B is Google's block-diffusion language model in the Gemma family: instead of left-to-right autoregression it denoises blocks of tokens in parallel. 25.8B total parameters with ~4B activated per token (128 experts, 8 active) and multimodal image-text input.

  • •Block-diffusion decoding — generates blocks of tokens in parallel rather than strictly left-to-right.
  • •MoE efficiency: 128 experts, 8 active per token (~4B activated of 26B total).
  • •Gemma-based multimodal (image-text) backbone with 256K context.
  • •Research-oriented alternative to autoregressive LLMs.

Modelos relacionados

Seu hardware

Detectando...

Escolhas rápidas

Melhor custo-benefícioA
Mac mini M4 64GB~$1,099 — 10 tok/s
NVIDIA
Melhor no geralS
RTX 5090 32GB~$1,999 — 144 tok/s

Melhor hardware

Melhores opções para DiffusionGemma 26B A4B

NVIDIA
RTX 5090 32GBS
32 GB
AMD Instinct MI100 32GBS
32 GB
NVIDIA
RTX PRO 4500 Blackwell 32GBS
32 GB
NVIDIA
NVIDIA V100 32GBA
32 GB
NVIDIA
NVIDIA A100 40GBA
40 GB

Rodar este modelo

DiffusionGemma 26B A4B on RTX 5090 32GBDiffusionGemma 26B A4B on AMD Instinct MI100 32GBDiffusionGemma 26B A4B on RTX PRO 4500 Blackwell 32GB

Opções de quantização

Estimativas de VRAM por nível de quantização

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
10.1 GB
Low—
Q3_K_S
3
12.6 GB
Low—
NVFP4
4
14.4 GB
Medium—
Q4_K_M
4
15.7 GB
Medium—
Q5_K_M
5
18.6 GB
High—
Q6_K
6
21.2 GB
High—
Q8_0
8
27.6 GB
Very High—
F16
16
52.9 GB
Maximum—

Compatibilidade de hardware

Estimativas de compatibilidade para todo o hardware

Abrir calculadora

Computing compatibility...

Detalhamento de memória

Reference: RTX 2060 6GB

Weights15.7 GB
KV Cache3.7 GB
Runtime2.4 GB
Headroom0.6 GB

Perguntas frequentes

FAQ — DiffusionGemma 26B A4B

Veja também

Guia de QuantizaçãoMetodologia de PontuaçãoAbrir calculadora