Google
DiffusionGemma 26B A4B
前沿
1.7M下载量1.1K点赞Jun 2026发布日期262K tokens上下文Apache 2.0许可证68 良好质量
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.
快速开始
— 复制粘贴即可本地运行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 99Quick 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
- •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.
相关模型
快速推荐
最佳硬件
DiffusionGemma 26B A4B 的最佳选择
运行此模型
量化选项
各量化级别的 VRAM 估算
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
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 | — |
硬件兼容性
全部硬件的适配估算
Computing compatibility...
内存详细分析
Reference: RTX 2060 6GB
Weights15.7 GB
KV Cache3.7 GB
Runtime2.4 GB
Headroom0.6 GB
常见问题
FAQ — DiffusionGemma 26B A4B
另请参阅