google · fine-tune of google/gemma-3-27b-pt
medgemma-27b-it
Runs on your machine
Choose a machine
We then show the largest format that fits, from real file sizes where we have them.
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: 1.0 GB, worked out from the model's config (ig1/medgemma-27b-it-FP8-Dynamic), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
weights context cache runtime
GGUF for llama.cpp, Ollama, LM Studio and others
unsloth/medgemma-27b-it-GGUF (converted by unsloth), 8.8k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-BF16.gguf (0.80 GB), not counted below. Showing the common levels.
| Format | Size | Memory needed | Memory | Get it |
|---|---|---|---|---|
| Q4_K_M | 15.4 GBfile size | 16.9 GB15.4 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/medgemma-27b-it-GGUF:Q4_K_MOllama ollama run hf.co/unsloth/medgemma-27b-it-GGUF:Q4_K_MDownload hf download unsloth/medgemma-27b-it-GGUF --include "medgemma-27b-it-Q4_K_M.gguf" --local-dir medgemma-27b-it-GGUF | |
| Q5_K_M | 17.9 GBfile size | 19.5 GB17.9 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/medgemma-27b-it-GGUF:Q5_K_MOllama ollama run hf.co/unsloth/medgemma-27b-it-GGUF:Q5_K_MDownload hf download unsloth/medgemma-27b-it-GGUF --include "medgemma-27b-it-Q5_K_M.gguf" --local-dir medgemma-27b-it-GGUF | |
| Q6_K | 20.6 GBfile size | 22.2 GB20.6 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/medgemma-27b-it-GGUF:Q6_KOllama ollama run hf.co/unsloth/medgemma-27b-it-GGUF:Q6_KDownload hf download unsloth/medgemma-27b-it-GGUF --include "medgemma-27b-it-Q6_K.gguf" --local-dir medgemma-27b-it-GGUF | |
| Q8_0 | 26.7 GBfile size | 28.3 GB26.7 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/medgemma-27b-it-GGUF:Q8_0Ollama ollama run hf.co/unsloth/medgemma-27b-it-GGUF:Q8_0Download hf download unsloth/medgemma-27b-it-GGUF --include "medgemma-27b-it-Q8_0.gguf" --local-dir medgemma-27b-it-GGUF | |
| BF16 | 50.3 GBfile size, 2 parts | 51.8 GB50.3 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/medgemma-27b-it-GGUF:BF16Download hf download unsloth/medgemma-27b-it-GGUF --include "BF16/medgemma-27b-it-BF16-*-of-00002.gguf" --local-dir medgemma-27b-it-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| MLX 5bitandosen/medgemma-27b-it-mlx-5Bit | 17.3 GBfile size | 18.8 GB17.3 + 1.0 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| BF16original weights | 51.1 GBfile size | 52.6 GB51.1 + 1.0 + 0.50 |
hf download google/medgemma-27b-it --local-dir medgemma-27b-itOther conversions (4; sizes not read)
- ig1/medgemma-27b-it-FP8-Dynamic FP8, 1.3k downloads
- suitch/medgemma-27b-it-4bit bitsandbytes, 4bit, 46 downloads
- ivangalkindeveloper/medgemma-27b-it-nvfp4 NVFP4, 37 downloads
- Prince-1/medgemma-27b-it Other, 7 downloads
The Hub tags 17 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.
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.