Caveman
Compressionlive

CaveGemma

Why use many token when few do trick — now baked in weights

A fine-tune of google/gemma-4-31B-it that speaks caveman without a system prompt or skill file. Across 193 held-out pairs it used 27% fewer output tokens, with code-fence exactness between 96.3% and 100%.

Product demo / CaveGemma

illustrative output comparison

prompt · no system prompt

Reverse a singly linked list in Python.

Flip each node next-pointer to prev. O(n) time, O(1) space.

```python
def reverse(head):
    prev = None
    while head:
        head.next, prev, head = prev, head, head.next
    return prev
```

tokens

49144

saved

66%

illustrative estimate · ~4 chars/token

code-fence exactness96–100%
semantic similarity0.91–0.98
fewer output tokens27%

illustrative response pair · product figures from 193 held-out pairs

Capability ledger

06
  1. 0127% fewer output tokens across 193 held-out pairs (weighted mean)
  2. 0296–100% code-fence exactness; semantic similarity 0.91–0.98
  3. 03Article density 0.005–0.020 on sources that measured 0.080
  4. 04Merged weights (62.5GB) or a 534MB LoRA adapter
  5. 05QLoRA rank 16; loads through Hugging Face transformers
  6. 06Text-only evaluation; multimodal behavior remains untested

Product ledger

02
Language
Python
License
MIT · weights inherit Gemma terms

Product index

05