willitrun·ai

GoogleGoogle

DiffusionGemma 26B A4B

Frontera
huggingfaceHuggingFace
1.7MDescargas1.1KMe gustaJun 2026Publicado262K tokensContextoApache 2.0Licencia68 BuenoCalidad

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.

Comenzar

— copia y pega para ejecutar en local

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

Tu hardware

Detectando...

Selecciones rápidas

Mejor económicoA
Mac mini M4 64GB~$1,099 — 10 tok/s
NVIDIA
Mejor en generalS
RTX 5090 32GB~$1,999 — 144 tok/s

Mejor hardware

Mejores opciones 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

Ejecutar este modelo

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

Opciones de cuantización

Estimaciones de VRAM por nivel de cuantización

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—

Compatibilidad de hardware

Estimaciones de encaje en todo el hardware

Abrir calculadora

Computing compatibility...

Desglose de memoria

Reference: RTX 2060 6GB

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

Preguntas frecuentes

FAQ — DiffusionGemma 26B A4B

Ver también

Guía de cuantizaciónMetodología de puntuaciónAbrir calculadora