- Size
- 25.8B parameters, 4.0B active (from the repo name)counted from the safetensors header on the Hub
- Licence
- custom, read it, Apache License 2.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 9 Jun 2026the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)DiffusionGemmaForBlockDiffusion
- On Hugging Face
- google/diffusiongemma-26B-A4B-it599k downloads in the last 30 days, 1.3k likes
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.35 GB, worked out from the model's config (google/diffusiongemma-26B-A4B-it), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
unsloth/diffusiongemma-26B-A4B-it-GGUF (converted by unsloth), 19k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q4_K_M | 15.7 GBfile size | 16.5 GB15.7 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:Q4_K_MOllama ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q4_K_MDownload hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-Q4_K_M.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF |
| Q5_K_M | 17.8 GBfile size | 18.7 GB17.8 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:Q5_K_MOllama ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q5_K_MDownload hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-Q5_K_M.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF |
| Q6_K | 21.1 GBfile size | 22.0 GB21.1 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:Q6_KOllama ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q6_KDownload hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-Q6_K.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF |
| Q8_0 | 25.0 GBfile size | 25.9 GB25.0 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:Q8_0Ollama ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q8_0Download hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-Q8_0.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF |
| BF16 | 47.1 GBfile size | 47.9 GB47.1 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:BF16Ollama ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:BF16Download hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-BF16.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitmlx-community/diffusiongemma-26B-A4B-it-4bit | 15.4 GBfile size | 16.3 GB15.4 + 0.35 + 0.50 | Download page |
| MLX 4bitmlx-community/diffusiongemma-26B-A4B-it-OptiQ-4bit | 16.6 GBfile size | 17.4 GB16.6 + 0.35 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 48.1 GBfile size | 49.0 GB48.1 + 0.35 + 0.50 |
hf download google/diffusiongemma-26B-A4B-it --local-dir diffusiongemma-26B-A4B-itOther conversions (11; sizes not read)
- nvidia/diffusiongemma-26B-A4B-it-NVFP4 NVFP4, 23k downloads
- RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic FP8, 12k downloads
- RedHatAI/diffusiongemma-26B-A4B-it-NVFP4 NVFP4, 10k downloads
- cyankiwi/diffusiongemma-26B-A4B-it-AWQ-INT4 AWQ, int4, 1.1k downloads
- Intel/diffusiongemma-26B-A4B-it-int4-AutoRound Other, int4, 730 downloads
- pixelkaiser/diffusiongemma-26B-A4B-it-AWQ-MLP-W4A16-G64-S32-L1024 AWQ, w4a16, 121 downloads
- aidendle94/diffusiongemma-26B-A4B-it-INT8-dynamic Other, int8, 91 downloads
- Jemimol-Technologies/diffusiongemma-26B-A4B-it-NVFP4-mirror NVFP4, 79 downloads
- PhysShell/diffusiongemma-26B-A4B-it-NVFP4 NVFP4, 25 downloads
- ozyjay/diffusiongemma-26b-a4b-it-modeldeck-gptq-q4-g32 GPTQ, 22 downloads
- jajmangold/diffusiongemma-26B-A4B-it-fni8 Other, 0 downloads
The Hub tags 37 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- unsloth/diffusiongemma-26B-A4B-it25.8B7.9kUnreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.