Compare model versions

Diff

Before

<div align="center">

<a href="https://www.orcarouter.ai" target="_blank">
  <img src="https://www.orcarouter.ai/orca-logo-classic.png" alt="OrcaRouter" width="110">
</a>

<h1>GLM-5.3-Flash-MLX</h1>

<p><em>An MLX build of the official GLM-5.3-Flash — 2bit-lite / 2 / 3 / 4 / 6-bit OrcaSAQ quant for Apple Silicon &amp; MLX</em></p>


<!-- orcacyber-promo:start -->
<table>
<tr>
<td width="150" style="vertical-align: middle;">
<div align="center"><a href="https://www.orcarouter.ai/models/orca/orcacyber-zero-1.5"><img src="https://www.orcarouter.ai/orca-logo-classic.png" width="90" alt="OrcaCyber Zero 1.5"></a></div>
</td>
<td>
<p>🛡️ <strong>New from Orca &mdash; <a href="https://www.orcarouter.ai/models/orca/orcacyber-zero-1.5">OrcaCyber Zero 1.5</a></strong></p>
<p>Post-trained for cybersecurity: vulnerability analysis, vulnerability reproduction, red teaming &amp; offensive-security research. <strong>98.01% pass@1 on CyberGym Level&nbsp;1</strong> &middot; 1M context &middot; function calling &middot; OpenAI-compatible API.</p>
<p><a href="https://www.orcarouter.ai/models/orca/orcacyber-zero-1.5"><img src="https://img.shields.io/badge/Try%20it%20on%20OrcaRouter%20%E2%86%92-FF6A00?style=for-the-badge&amp;labelColor=0B1F3A" alt="Try it on OrcaRouter"></a></p>
</td>
</tr>
</table>
<!-- orcacyber-promo:end -->

<p><strong>▶ <a href="https://www.orcarouter.ai/models/z-ai/glm-5.3-flash">Run GLM-5.3-Flash instantly on the OrcaRouter API</a></strong> — no download, full precision.</p>

<p>
<a href="https://www.orcarouter.ai"><img src="https://img.shields.io/badge/Website-orcarouter.ai-1E6FEB" alt="Website"></a>
<a href="https://www.orcarouter.ai/models"><img src="https://img.shields.io/badge/OrcaRouter-Model%20Catalog-2EA043" alt="Model Catalog"></a>
<a href="https://www.orcarouter.ai/models/z-ai/glm-5.3-flash"><img src="https://img.shields.io/badge/OrcaRouter-Hosted%20API-6F42C1" alt="Hosted API"></a>
<a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-4C8BF5" alt="License"></a>
<img src="https://img.shields.io/badge/Format-MLX-00A67E" alt="MLX">
<img src="https://img.shields.io/badge/Quants-lite%20|%202%20|%203%20|%204%20|%206--bit-FF8800" alt="Quants">
<img src="https://img.shields.io/badge/Method-OrcaSAQ-E67E22" alt="OrcaSAQ">
<img src="https://img.shields.io/badge/Vision%20%2B%20indexer-BF16-9B59B6" alt="BF16">
<a href="https://github.com/Continuum-AI-Corp/Orca-Code-Review"><img src="https://img.shields.io/badge/OrcaCode-Review-181717?logo=github" alt="OrcaCode Review"></a>
</p>

<p><strong>One Gateway. Every Model.</strong> — Route Smarter · Ship Safer · Spend Less.<br>
<a href="https://www.orcarouter.ai/models/z-ai/glm-5.3-flash">GLM-5.3-Flash on OrcaRouter →</a></p>

<p>
<a href="https://www.orcarouter.ai">Website</a> ·
<a href="https://www.orcarouter.ai/models">Model Catalog</a> ·
<a href="https://www.orcarouter.ai/models/z-ai/glm-5.3-flash">Model API</a> ·
<a href="https://github.com/Continuum-AI-Corp">GitHub</a> ·
<a href="https://github.com/Continuum-AI-Corp/Orca-Code-Review">OrcaCode Review</a> ·
<a href="https://discord.gg/yAh6Tex6kx">Discord</a> ·
<a href="https://x.com/OrcaRouter">X</a>
</p>

</div>

---

> An **MLX** build of the official [`zai-org/GLM-5.3-Flash`](https://huggingface.co/zai-org/GLM-5.3-Flash)
> — a **320B-total / 18B-active** MoE, the first natively multimodal model in the GLM-5 series, built on
> the new **`glm5_next`** hybrid architecture (sparse + linear attention with Manifold-Constrained
> Hyper-Connections) — quantized to **MLX** for **Apple Silicon** and the MLX CUDA backend. Five
> builds (**2bit-lite / 2 / 3 / 4 / 6-bit**) ship as subfolders, with the **4-bit build mirrored at the repo root**,
> produced with **OrcaSAQ (Sensitivity-Aware Quantization)** — calibration-free and
> architecture-aware: sensitive tensors get more bits
> (shared experts `+2`, `down_proj` `+1`), and every tensor that was *not* FP8 in the base release —
> **the 34 linear-attention layers, the sparse indexer, hyper-connections, norms, `embed_tokens`,
> `lm_head`, and the entire vision tower — is carried through in BF16**. The four projections of the
> sparse-attention blocks *were* FP8 upstream and are quantized at the base width. Browse all models in the
> [OrcaRouter Model Catalog](https://www.orcarouter.ai/models); deployed as API
> [here](https://www.orcarouter.ai/models/z-ai/glm-5.3-flash). Put this model to work reviewing your
> pull requests with **[OrcaCode Review](https://github.com/Continuum-AI-Corp/Orca-Code-Review)**.

---

After

<div align="center">

<a href="https://www.orcarouter.ai" target="_blank">
  <img src="https://www.orcarouter.ai/orca-logo-classic.png" alt="OrcaRouter" width="110">
</a>

<h1>GLM-5.3-Flash-MLX</h1>

<p><em>An MLX build of the official GLM-5.3-Flash — 2bit-lite / 2 / 3 / 4 / 6-bit OrcaSAQ quant for Apple Silicon &amp; MLX</em></p>


<!-- orcacyber-promo:start -->
<table>
<tr>
<td width="150" style="vertical-align: middle;">
<div align="center"><a href="https://www.orcarouter.ai/models/orca/orcacyber-zero-1.5"><img src="https://www.orcarouter.ai/orca-logo-classic.png" width="90" alt="OrcaCyber Zero 1.5"></a></div>
</td>
<td>
<p>🛡️ <strong>New from Orca &mdash; <a href="https://www.orcarouter.ai/models/orca/orcacyber-zero-1.5">OrcaCyber Zero 1.5</a></strong></p>
<p>Post-trained for cybersecurity: vulnerability analysis, vulnerability reproduction, red teaming &amp; offensive-security research. <strong>98.01% pass@1 on CyberGym Level&nbsp;1</strong> &middot; 1M context &middot; function calling &middot; OpenAI-compatible API.</p>
<p><a href="https://www.orcarouter.ai/models/orca/orcacyber-zero-1.5"><img src="https://img.shields.io/badge/Try%20it%20on%20OrcaRouter%20%E2%86%92-FF6A00?style=for-the-badge&amp;labelColor=0B1F3A" alt="Try it on OrcaRouter"></a></p>
</td>
</tr>
<tr>
<td colspan="2">
<p>🔌 <strong>New from Orca &mdash; <a href="https://www.orcarouter.ai/solutions/orca-connect">Orca Connect</a></strong></p>
<p>Have a rig running Ollama, LM Studio, vLLM, llama.cpp or SGLang? <strong>Orca Connect</strong> puts it behind your usual OrcaRouter API key, next to 200+ hosted models, reachable from a laptop, a phone or a cloud agent. Outbound only: no port forwarding, no tunnel, no firewall rule. <strong>Requests your own hardware serves cost $0</strong>, and <code>orca-connect claude</code> points Claude Code at your rig for one session.</p>
<video src="https://huggingface.co/spaces/orcarouter/README/resolve/main/assets/orca-connect.mp4" controls autoplay muted loop playsinline width="100%"></video>
<p><a href="https://www.orcarouter.ai/solutions/orca-connect"><img src="https://img.shields.io/badge/Connect%20your%20rig%20%E2%86%92-FF6A00?style=for-the-badge&amp;labelColor=0B1F3A" alt="Connect your rig"></a></p>
</td>
</tr>
</table>
<!-- orcacyber-promo:end -->

<p><strong>▶ <a href="https://www.orcarouter.ai/models/z-ai/glm-5.3-flash">Run GLM-5.3-Flash instantly on the OrcaRouter API</a></strong> — no download, full precision.</p>

<p>
<a href="https://www.orcarouter.ai"><img src="https://img.shields.io/badge/Website-orcarouter.ai-1E6FEB" alt="Website"></a>
<a href="https://www.orcarouter.ai/models"><img src="https://img.shields.io/badge/OrcaRouter-Model%20Catalog-2EA043" alt="Model Catalog"></a>
<a href="https://www.orcarouter.ai/models/z-ai/glm-5.3-flash"><img src="https://img.shields.io/badge/OrcaRouter-Hosted%20API-6F42C1" alt="Hosted API"></a>
<a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-4C8BF5" alt="License"></a>
<img src="https://img.shields.io/badge/Format-MLX-00A67E" alt="MLX">
<img src="https://img.shields.io/badge/Quants-lite%20|%202%20|%203%20|%204%20|%206--bit-FF8800" alt="Quants">
<img src="https://img.shields.io/badge/Method-OrcaSAQ-E67E22" alt="OrcaSAQ">
<img src="https://img.shields.io/badge/Vision%20%2B%20indexer-BF16-9B59B6" alt="BF16">
<a href="https://github.com/Continuum-AI-Corp/Orca-Code-Review"><img src="https://img.shields.io/badge/OrcaCode-Review-181717?logo=github" alt="OrcaCode Review"></a>
</p>

<p><strong>One Gateway. Every Model.</strong> — Route Smarter · Ship Safer · Spend Less.<br>
<a href="https://www.orcarouter.ai/models/z-ai/glm-5.3-flash">GLM-5.3-Flash on OrcaRouter →</a></p>

<p>
<a href="https://www.orcarouter.ai">Website</a> ·
<a href="https://www.orcarouter.ai/models">Model Catalog</a> ·
<a href="https://www.orcarouter.ai/models/z-ai/glm-5.3-flash">Model API</a> ·
<a href="https://github.com/Continuum-AI-Corp">GitHub</a> ·
<a href="https://github.com/Continuum-AI-Corp/Orca-Code-Review">OrcaCode Review</a> ·
<a href="https://discord.gg/yAh6Tex6kx">Discord</a> ·
<a href="https://x.com/OrcaRouter">X</a>
</p>

</div>

---

> An **MLX** build of the official [`zai-org/GLM-5.3-Flash`](https://huggingface.co/zai-org/GLM-5.3-Flash)
> — a **320B-total / 18B-active** MoE, the first natively multimodal model in the GLM-5 series, built on
> the new **`glm5_next`** hybrid architecture (sparse + linear attention with Manifold-Constrained
> Hyper-Connections) — quantized to **MLX** for **Apple Silicon** and the MLX CUDA backend. Five
> builds (**2bit-lite / 2 / 3 / 4 / 6-bit**) ship as subfolders, with the **4-bit build mirrored at the repo root**,
> produced with **OrcaSAQ (Sensitivity-Aware Quantization)** — calibration-free and
> architecture-aware: sensitive tensors get more bits
> (shared experts `+2`, `down_proj` `+1`), and every tensor that was *not* FP8 in the base release —
> **the 34 linear-attention layers, the sparse indexer, hyper-connections, norms, `embed_tokens`,
> `lm_head`, and the entire vision tower — is carried through in BF16**. The four projections of the
> sparse-attention blocks *were* FP8 upstream and are quantized at the base width. Browse all models in the
> [OrcaRouter Model Catalog](https://www.orcarouter.ai/models); deployed as API
> [here](https://www.orcarouter.ai/models/z-ai/glm-5.3-flash). Put this model to work reviewing your
> pull requests with **[OrcaCode Review](https://github.com/Continuum-AI-Corp/Orca-Code-Review)**.

1 more line not shown.