Skip to content

docs(guide): 'When to use which?' table + C code in CTA #39

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
unamedkr merged 1 commit into from
Apr 10, 2026
+38 −5
Merged

docs(guide): 'When to use which?' table + C code in CTA #39

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 38 additions & 5 deletions site/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -480,7 +480,7 @@ <h3 class="reveal">Compression vs Quality</h3>
</table>
</div>

<h3 class="reveal">vs llama.cpp</h3>
<h3 class="reveal">vs llama.cpp KV compression</h3>
<p class="reveal">Same 4-bit budget, 3.5x less quality degradation:</p>
<div class="viz reveal">
<div class="viz-title">PPL Degradation at 4-bit (lower is better)</div>
Expand All @@ -494,6 +494,23 @@ <h3 class="reveal">vs llama.cpp</h3>
</div>
</div>

<h3 class="reveal" style="margin-top:3rem">When to use which?</h3>
<p class="reveal" style="color:var(--text2);margin-bottom:1rem">llama.cpp is excellent. The difference is integration scope, not capability:</p>
<div class="reveal" style="overflow-x:auto">
<table>
<thead><tr><th>Scenario</th><th>quant.cpp</th><th>llama.cpp</th></tr></thead>
<tbody>
<tr><td>WASM browser demo</td><td style="color:var(--green)">192 KB binary</td><td style="color:var(--text2)">Tensor graph too large</td></tr>
<tr><td>Microcontroller / RTOS</td><td style="color:var(--green)">#include only</td><td style="color:var(--text2)">Needs build system</td></tr>
<tr><td>Game engine plugin</td><td style="color:var(--green)">Drop one .h file</td><td style="color:var(--text2)">250K LOC build</td></tr>
<tr><td>Learn in an afternoon</td><td style="color:var(--green)">16K LOC</td><td style="color:var(--text2)">250K+ LOC</td></tr>
<tr><td>GPU throughput</td><td style="color:var(--text2)">Basic</td><td style="color:var(--green)">Full Metal/CUDA</td></tr>
<tr><td>Model coverage</td><td style="color:var(--text2)">7 architectures</td><td style="color:var(--green)">100+</td></tr>
</tbody>
</table>
</div>
<p class="reveal" style="color:var(--text2);font-size:0.85rem;margin-top:0.5rem">Use llama.cpp for speed on a workstation. Use quant.cpp when you need to ship LLM inference <em>inside</em> something.</p>

<h3 class="reveal">Context Length on 8GB Mac</h3>
<div class="reveal">
<table>
Expand Down Expand Up @@ -572,12 +589,28 @@ <h2 class="reveal" data-i18n="gl.title">Glossary</h2>
<section class="cta" style="background:var(--bg2)">
<div class="container reveal">
<h2 style="margin-bottom:1rem" data-i18n="cta.title">Try It Yourself</h2>
<p style="color:var(--text2);margin-bottom:2rem;max-width:500px;margin-left:auto;margin-right:auto" data-i18n="cta.desc">Three lines of Python. No GPU, no API key, no setup.</p>
<pre style="text-align:left;display:inline-block;margin-bottom:2rem"><code>pip install quantcpp
<p style="color:var(--text2);margin-bottom:2rem;max-width:560px;margin-left:auto;margin-right:auto" data-i18n="cta.desc">Python one-liner or C single-header. No GPU, no API key, no setup.</p>
<div style="display:flex;gap:1.5rem;flex-wrap:wrap;justify-content:center;margin-bottom:2rem;text-align:left">
<div>
<div style="font-size:0.75rem;color:var(--text2);margin-bottom:0.3rem;font-weight:600">Python</div>
<pre style="margin:0"><code>pip install quantcpp

from quantcpp import Model
m = Model.from_pretrained("Llama-3.2-1B")
print(m.ask("What is gravity?"))</code></pre>
</div>
<div>
<div style="font-size:0.75rem;color:var(--text2);margin-bottom:0.3rem;font-weight:600">C (single header)</div>
<pre style="margin:0"><code>#include "quant.h"

int main() {
quant_model* m = quant_load("model.gguf");
quant_generate(quant_new(m, NULL),
"Hello!", print_token, NULL);
}
// cc app.c -lm -lpthread</code></pre>
</div>
</div>
<br>
<a href="https://github.com/quantumaikr/quant.cpp" class="cta-btn cta-primary">GitHub</a>
<a href="https://pypi.org/project/quantcpp/" class="cta-btn cta-secondary">PyPI</a>
Expand Down Expand Up @@ -715,7 +748,7 @@ <h2 style="margin-bottom:1rem" data-i18n="cta.title">Try It Yourself</h2>
'ch5.label':'Chapter 5','ch5.title':'Benchmarks','ch5.desc':'All measurements on Llama 3.2 1B Instruct (Q8_0 GGUF), Apple M1 Pro, 8 threads.',
'ch6.label':'Chapter 6','ch6.title':'Research Foundations','ch6.desc':'Each technique in quant.cpp is grounded in peer-reviewed research:',
'gl.label':'Reference','gl.title':'Glossary',
'cta.title':'Try It Yourself','cta.desc':'Three lines of Python. No GPU, no API key, no setup.',
'cta.title':'Try It Yourself','cta.desc':'Python one-liner or C single-header. No GPU, no API key, no setup.',
},
ko: {
'nav.problem':'문제점','nav.solution':'핵심 발견','nav.techniques':'4가지 기술',
Expand Down Expand Up @@ -748,7 +781,7 @@ <h2 style="margin-bottom:1rem" data-i18n="cta.title">Try It Yourself</h2>
'ch5.label':'챕터 5','ch5.title':'벤치마크','ch5.desc':'모든 측정: Llama 3.2 1B Instruct (Q8_0 GGUF), Apple M1 Pro, 8 스레드.',
'ch6.label':'챕터 6','ch6.title':'연구 기반','ch6.desc':'quant.cpp의 각 기술은 동료 심사를 거친 연구에 기반합니다:',
'gl.label':'참조','gl.title':'용어집',
'cta.title':'직접 해보기','cta.desc':'Python 3줄. GPU도, API 키도, 설정도 필요 없습니다.',
'cta.title':'직접 해보기','cta.desc':'Python 한 줄 또는 C 헤더 하나. GPU도, API 키도, 설정도 필요 없습니다.',
}
};

Expand Down
Loading