kavai/ Caveman-Library

140 Downloads Updated 3 weeks ago

🪨 caveman be better. more save token. token be less. model be library

vision tools thinking audio

ollama run kavai/Caveman-Library:gemma4-26b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "kavai/Caveman-Library:gemma4-26b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='kavai/Caveman-Library:gemma4-26b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'kavai/Caveman-Library:gemma4-26b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model kavai/Caveman-Library:gemma4-26b

OpenClaw

OpenClaw ollama launch openclaw --model kavai/Caveman-Library:gemma4-26b

Hermes Agent

Hermes Agent ollama launch hermes --model kavai/Caveman-Library:gemma4-26b

Codex

Codex ollama launch codex --model kavai/Caveman-Library:gemma4-26b

OpenCode

OpenCode ollama launch opencode --model kavai/Caveman-Library:gemma4-26b

Models

Name

37 models

Size

Context

Input

Caveman-Library:gemma4-26b

18GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:gemma4-26b

18GB

256K

Text, Image

Caveman-Library:gemma4-31b

20GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:gemma4-31b

20GB

256K

Text, Image

Caveman-Library:gemma4-e2b

7.2GB · 128K context window · Text, Image · 3 weeks ago

Caveman-Library:gemma4-e2b

7.2GB

128K

Text, Image

Caveman-Library:gemma4-e4b

9.6GB · 128K context window · Text, Image · 3 weeks ago

Caveman-Library:gemma4-e4b

9.6GB

128K

Text, Image

Caveman-Library:lfm2-24b

14GB · 32K context window · Text · 3 weeks ago

Caveman-Library:lfm2-24b

14GB

32K

Text

Caveman-Library:llama3-1-405b

243GB · 128K context window · Text · 3 weeks ago

Caveman-Library:llama3-1-405b

243GB

128K

Text

Caveman-Library:llama3-1-70b

43GB · 128K context window · Text · 3 weeks ago

Caveman-Library:llama3-1-70b

43GB

128K

Text

Caveman-Library:llama3-1-8b

4.9GB · 128K context window · Text · 3 weeks ago

Caveman-Library:llama3-1-8b

4.9GB

128K

Text

Caveman-Library:nemotron-3-super-120b

87GB · 256K context window · Text · 3 weeks ago

Caveman-Library:nemotron-3-super-120b

87GB

256K

Text

Caveman-Library:nemotron-cascade-2-30b

24GB · 256K context window · Text · 3 weeks ago

Caveman-Library:nemotron-cascade-2-30b

24GB

256K

Text

Caveman-Library:qwen3-5-0.8b

1.0GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-5-0.8b

1.0GB

256K

Text, Image

Caveman-Library:qwen3-5-122b

81GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-5-122b

81GB

256K

Text, Image

Caveman-Library:qwen3-5-27b

17GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-5-27b

17GB

256K

Text, Image

Caveman-Library:qwen3-5-2b

2.7GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-5-2b

2.7GB

256K

Text, Image

Caveman-Library:qwen3-5-35b

24GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-5-35b

24GB

256K

Text, Image

Caveman-Library:qwen3-5-4b

3.4GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-5-4b

3.4GB

256K

Text, Image

Caveman-Library:qwen3-5-9b

6.6GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-5-9b

6.6GB

256K

Text, Image

Caveman-Library:qwen3-next-80b

50GB · 256K context window · Text · 3 weeks ago

Caveman-Library:qwen3-next-80b

50GB

256K

Text

Caveman-Library:qwen3-vl-235b

143GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-235b

143GB

256K

Text, Image

Caveman-Library:qwen3-vl-235b-a22b-instruct

143GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-235b-a22b-instruct

143GB

256K

Text, Image

Caveman-Library:qwen3-vl-235b-a22b-thinking

143GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-235b-a22b-thinking

143GB

256K

Text, Image

Caveman-Library:qwen3-vl-2b

1.9GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-2b

1.9GB

256K

Text, Image

Caveman-Library:qwen3-vl-2b-instruct

1.9GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-2b-instruct

1.9GB

256K

Text, Image

Caveman-Library:qwen3-vl-2b-thinking

1.9GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-2b-thinking

1.9GB

256K

Text, Image

Caveman-Library:qwen3-vl-30b

20GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-30b

20GB

256K

Text, Image

Caveman-Library:qwen3-vl-30b-a3b

20GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-30b-a3b

20GB

256K

Text, Image

Caveman-Library:qwen3-vl-30b-a3b-instruct

20GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-30b-a3b-instruct

20GB

256K

Text, Image

Caveman-Library:qwen3-vl-30b-a3b-thinking

20GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-30b-a3b-thinking

20GB

256K

Text, Image

Caveman-Library:qwen3-vl-32b

21GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-32b

21GB

256K

Text, Image

Caveman-Library:qwen3-vl-32b-instruct

21GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-32b-instruct

21GB

256K

Text, Image

Caveman-Library:qwen3-vl-32b-thinking

21GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-32b-thinking

21GB

256K

Text, Image

Caveman-Library:qwen3-vl-4b

3.3GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-4b

3.3GB

256K

Text, Image

Caveman-Library:qwen3-vl-4b-instruct

3.3GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-4b-instruct

3.3GB

256K

Text, Image

Caveman-Library:qwen3-vl-4b-thinking

3.3GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-4b-thinking

3.3GB

256K

Text, Image

Caveman-Library:qwen3-vl-8b

6.1GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-8b

6.1GB

256K

Text, Image

Caveman-Library:qwen3-vl-8b-instruct

6.1GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-8b-instruct

6.1GB

256K

Text, Image

Caveman-Library:qwen3-vl-8b-thinking

6.1GB · 256K context window · Text, Image · 3 weeks ago

Caveman-Library:qwen3-vl-8b-thinking

6.1GB

256K

Text, Image

Readme

Caveman Model Lib 🪨 (Model be no my)

LLM speak caveman. Few words. Same brain power. Less tokens.

What Model Do

Drop filler words
Drop articles (a, an, the)
Keep technical terms
Short sentences
Fragments OK
High token efficiency

Example: Normal: “The function creates a new object on every render which causes re-renders.” Caveman: “New object each render. New ref. Re-render.”

Modes

Full Mode

Short words
Fragments
Clear meaning

Example: Inline object prop. New ref. Component re-render. Use useMemo.

Ultra Mode

Abbrev
Arrows
Minimal words

Example: Inline obj → new ref → re-render. useMemo.

Rules

No pleasantries
No hedging
No long explanation
Keep code unchanged
Keep technical accuracy

Pattern: [thing] [action] [reason]. [next step]

Example: State change. New render. Expensive calc repeat. Memoize.

Use Cases

Token saving
Fast debugging
Logs
CLI tools
Agent responses
Low bandwidth chat

Not Good For

Formal writing
Legal text
UX copy
Friendly conversation

Quick Test

Input: Explain why React component re-renders when passing inline object.

Output: Inline object new each render. Ref change. Props diff. Re-render. useMemo.

Goal

Less words. Same meaning. Max efficiency.

# Caveman Model Lib 🪨 (Model be no my)

LLM speak caveman.
Few words.
Same brain power.
Less tokens.

---

## What Model Do

* Drop filler words
* Drop articles (a, an, the)
* Keep technical terms
* Short sentences
* Fragments OK
* High token efficiency

Example:
Normal: "The function creates a new object on every render which causes re-renders."
Caveman: "New object each render. New ref. Re-render."

---

## Modes

### Full Mode

* Short words
* Fragments
* Clear meaning

Example:
`Inline object prop. New ref. Component re-render. Use useMemo.`

### Ultra Mode

* Abbrev
* Arrows
* Minimal words

Example:
`Inline obj → new ref → re-render. useMemo.`

---

## Rules

* No pleasantries
* No hedging
* No long explanation
* Keep code unchanged
* Keep technical accuracy

Pattern:
`[thing] [action] [reason]. [next step]`

Example:
`State change. New render. Expensive calc repeat. Memoize.`

---

## Use Cases

* Token saving
* Fast debugging
* Logs
* CLI tools
* Agent responses
* Low bandwidth chat

---

## Not Good For

* Formal writing
* Legal text
* UX copy
* Friendly conversation

---

## Quick Test

Input:
`Explain why React component re-renders when passing inline object.`

Output:
`Inline object new each render. Ref change. Props diff. Re-render. useMemo.`

---

## Goal

Less words.
Same meaning.
Max efficiency.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)