Google
Diffusiongemma 26B A4B It
Diffusiongemma 26B A4B It is an open-weights 26B-parameter model by Google. It holds an Intelligence score of 50.3 on the local.ai leaderboard (2026-08 snapshot).
MoEdiffusionopen weights
50.3
local.ai Intelligence
Parameters
26B
MoE · 4B active parameters
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2026-07-15
Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.
Does it fit your hardware?
Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.
Q4_K_M 15.1GQ6_K 23.4GQ8_0 28.6GFP16 52G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 7 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 9.4 GB | Very small |
| Q3_K_M | 12 GB | Small |
| NVFP4 | 13 GB | NVIDIA 4-bit |
| Q4_K_S | 14 GB | Common |
| Q4_K_M | 15.1 GB | Most common sweet spot |
| Q5_K_M | 19.8 GB | Balanced |
| Q6_K | 23.4 GB | Near-lossless |
| Q8_0 | 28.6 GB | Near-lossless |
| FP16 | 52 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| model-00005-of-00011.safetensors | 4.58 GB |
| model-00007-of-00011.safetensors | 4.58 GB |
| model-00009-of-00011.safetensors | 4.58 GB |
| model-00003-of-00011.safetensors | 4.58 GB |
| model-00006-of-00011.safetensors | 4.55 GB |
| model-00008-of-00011.safetensors | 4.55 GB |
GGUF: unsloth/diffusiongemma-26B-A4B-it-GGUF · 33,661 downloads
GGUF: yabaimimi/edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-GGUF · 13,117 downloads
| File | Size | |
|---|---|---|
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-BF16.gguf | 47.07 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-FP16.gguf | 47.07 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-IQ3_M.gguf | 11.55 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-IQ3_S.gguf | 11.39 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-IQ4_NL.gguf | 13.59 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-IQ4_XS.gguf | 13.11 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q2_K.gguf | 9.86 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q3_K_M.gguf | 12.38 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q4_K_M.gguf | 15.65 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q5_K_M.gguf | 17.83 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q6_K.gguf | 21.10 GB | download |
| edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q8_0.gguf | 25.03 GB | download |
What you save self-hosting this model
Uses the model's own API price when it exists; otherwise the closest commercial equivalent.
Waiting for hardware detection…
RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.