medgemma-27b-it How much memory it needs, what its licence allows, and whether it fits an office box.
Short answer. medgemma-27b-it needs about 18 GB of memory at 4-bit, 33 GB at 8-bit and 60 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 28.8 billion parameters and a 131,072-token context window. Licence in short: custom licence: check before commercial use. By memory alone, on ANVE’s launch configurations: ANVE One fits at 8-bit, ANVE Office fits at 4-bit, ANVE Office Pro (GPU) fits at 4-bit. These are estimates from its published size, not benchmarks.
01
What it is
medgemma-27b-it is a vision-language model: it reads images (scanned pages, photos, charts and screenshots) as well as text, published by Google on Hugging Face on 9 July 2025. It has about 28.8 billion parameters and a configured context window of 131,072 tokens.
Its card lists the licence as a custom licence (health-ai-developer-foundations). In short, the licence sets its own terms; read it before any commercial use. Access on Hugging Face requires accepting the publisher’s terms first.
Hugging Face counted about 48,679 downloads of it in the 30 days before we checked (7 Oct 2026), and 460 people have liked it there.
It is built on google/gemma-3-27b-pt, according to its card.
02
How much memory it needs
The arithmetic: parameters × bits per weight ÷ 8 gives the weights; add the KV cache, which grows with every token of context; then add about 1.5 GB for the runtime. These are estimates for planning, not measurements.
Each token of context adds about 0.08 MB of KV cache at 16-bit, so 32,768 tokens would add about 2.7 GB. 52 of its 62 layers use sliding-window attention, so the real cache is smaller than this full-attention estimate.
Precision
Weights
KV cache (8,192 tokens)
Total, estimated
BF16 (full precision)
58 GB
0.67 GB
60 GB
8-bit (Q8_0)
31 GB
0.67 GB
33 GB
4-bit (Q4_K)
16 GB
0.67 GB
18 GB
03
Architecture at a glance
Setting
Value in config.json
Architecture class
Gemma3ForConditionalGeneration
Model type
gemma3
Layers
62
Hidden size
5,376
Attention heads
32
Key-value heads
16 (grouped-query attention)
Head size
128
Vocabulary
262,208
Configured context
131,072
Stored precision
bfloat16
04
Will it fit on ANVE?
Arithmetic against the launch specification, not a test: about three quarters of ANVE One’s 64 GB of unified memory for the model (as AMD’s Variable Graphics Memory allows), and the 24 GB on the graphics card in ANVE Office and ANVE Office Pro, which keep the rest of the stack in 64 GB and 128 GB of system memory. ANVE’s tested default is Qwen 3.8 27B; this model is not yet validated on ANVE.
Configuration (at launch)
Memory for the model
Verdict
ANVE One
about 48 GB of 64 GB unified memory
fits at 8-bit
ANVE Office
24 GB on the RTX PRO 4000 Blackwell SFF Edition
fits at 4-bit
ANVE Office Pro (GPU)
24 GB on the RTX PRO 4000 Blackwell
fits at 4-bit
05
What an office would use it for
This is the class ANVE runs by default (27B-class): strong enough for meeting minutes, summaries, drafting and question answering over an office’s own documents, and small enough for one box.
06
Similar models to compare
Qwen3.8-27B (27.8B parameters, about 17 GB at 4-bit before context; commercial use allowed)
Qwen3.6-27B (27.8B parameters, about 17 GB at 4-bit before context; commercial use allowed)
Qwen3-VL-30B-A3B-Instruct (31.1B parameters, about 19 GB at 4-bit before context; commercial use allowed)
07
Questions people ask
How much memory does medgemma-27b-it need?
About 18 GB at 4-bit, 33 GB at 8-bit and 60 GB at full 16-bit precision, including an 8,192-token KV cache and about 1.5 GB of runtime overhead. These are estimates from its parameter count.
Can medgemma-27b-it run on a 24 GB graphics card?
Yes, at 4-bit by this estimate, with room left for context.
Is medgemma-27b-it free for commercial use?
Its card lists a custom licence (health-ai-developer-foundations), which sets its own terms; read it before any commercial use. Read the licence itself before relying on this summary; it is not legal advice.
What is medgemma-27b-it’s context window?
Its configuration sets 131,072 tokens. Longer contexts need more memory for the KV cache, so the practical limit on a given machine can be lower.
08
What is not real yet
No sealed ANVE unit exists; every image of the appliance on this site is a labelled render. The software runs today on a development machine. No customers yet, no certifications, no delivery date, and the final price is not announced.
Reservations are ₹999 in India or US$12 elsewhere, refundable in full until you confirm an order in writing (terms). Offices that cannot use cloud AI can apply to be one of ten design partners.
