Add MLX quantized model

README.md

@@ -0,0 +1,90 @@
+---
+base_model: openai/gpt-oss-120b
+library_name: mlx
+tags:
+  - rotorquant
+  - kv-cache-quantization
+  - gpt-oss
+  - openai
+  - moe
+  - quantized
+  - mlx
+  - 2bit
+license: apache-2.0
+pipeline_tag: text-generation
+---
+
+# GPT-OSS-120B - RotorQuant MLX 2-bit
+
+**2-bit weight-quantized MLX version** of [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) with RotorQuant KV-cache quantization. Optimized for Apple Silicon inference via the [MLX](https://github.com/ml-explore/mlx) framework. The smallest variant with RotorQuant's superior KV-cache throughput -- enables GPT-OSS-120B to fit on more accessible Mac hardware. GPT-OSS-120B is OpenAI's flagship open-weights Mixture-of-Experts model (Apache 2.0), approaching o4-mini quality for reasoning tasks.
+
+Approximate model size: **~30 GB**
+
+## Model Specifications
+
+| Property | Value |
+|---|---|
+| **Base Model** | [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) |
+| **Parameters** | 120 billion (MoE) |
+| **Architecture** | Mixture-of-Experts (MoE) Transformer |
+| **License** | Apache 2.0 (commercial use OK) |
+| **Weight Quantization** | 2-bit (~30 GB) |
+| **KV-Cache Quantization** | RotorQuant |
+| **Framework** | MLX (Apple Silicon) |
+
+## Quickstart
+
+```python
+from mlx_lm import load, generate
+from rotorquant import IsoQuantCache
+
+model, tokenizer = load("majentik/gpt-oss-120b-RotorQuant-MLX-2bit")
+
+prompt = "Explain the theory of relativity."
+response = generate(model, tokenizer, prompt=prompt, max_tokens=512)
+print(response)
+```
+
+## What is RotorQuant?
+
+[RotorQuant](https://github.com/scrya-com/rotorquant) applies block-diagonal rotations (Clifford algebra) for KV cache compression. Combined with aggressive 2-bit weight quantization in MLX, this produces the smallest possible footprint for GPT-OSS-120B while retaining RotorQuant's fast KV-cache throughput.
+
+Key advantages over TurboQuant:
+- **5.3x faster prefill**
+- **28% faster decode**
+- Equivalent memory savings
+
+## KV-Cache Quantization Comparison
+
+| Method | Prefill Speed | Decode Speed | Memory Savings | Reference |
+|---|---|---|---|---|
+| **TurboQuant** | 1x (baseline) | 1x (baseline) | High | [arXiv: 2504.19874](https://arxiv.org/abs/2504.19874) |
+| **RotorQuant** | **5.3x faster** | **28% faster** | High | [GitHub](https://github.com/scrya-com/rotorquant) |
+
+## Memory Estimates (GPT-OSS-120B)
+
+| Precision | Approximate Size | MLX Variant |
+|---|---|---|
+| BF16 (original) | ~240 GB | -- |
+| 8-bit quantized | ~120 GB | [RotorQuant-MLX-8bit](https://huggingface.co/majentik/gpt-oss-120b-RotorQuant-MLX-8bit) |
+| 4-bit quantized | ~65 GB | [RotorQuant-MLX-4bit](https://huggingface.co/majentik/gpt-oss-120b-RotorQuant-MLX-4bit) |
+| **2-bit quantized** | **~30 GB** | **This model** |
+
+## Hardware Requirements
+
+This model requires approximately 30 GB of unified memory. Recommended hardware:
+- Apple M1 Max (32 GB+)
+- Apple M2 Max (32 GB+)
+- Apple M3 Max (36 GB+)
+- Apple M4 Max (36 GB+)
+- Any Apple Silicon Mac with 36 GB+ unified memory
+
+## See Also
+
+- [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) -- Base model
+- [majentik/gpt-oss-120b-RotorQuant](https://huggingface.co/majentik/gpt-oss-120b-RotorQuant) -- RotorQuant KV-cache only (transformers)
+- [majentik/gpt-oss-120b-RotorQuant-MLX-8bit](https://huggingface.co/majentik/gpt-oss-120b-RotorQuant-MLX-8bit) -- MLX 8-bit variant
+- [majentik/gpt-oss-120b-RotorQuant-MLX-4bit](https://huggingface.co/majentik/gpt-oss-120b-RotorQuant-MLX-4bit) -- MLX 4-bit variant
+- [majentik/gpt-oss-120b-TurboQuant-MLX-2bit](https://huggingface.co/majentik/gpt-oss-120b-TurboQuant-MLX-2bit) -- TurboQuant MLX 2-bit variant
+- [RotorQuant GitHub](https://github.com/scrya-com/rotorquant)
+- [MLX Framework](https://github.com/ml-explore/mlx)

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb5b10b2228a5db879375e9ba6d0bd5f1e70094051adcb14b7c6a0a01513634
+size 5298258962

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3084c20993a1bfe8ac653f1b981a841d1f719e8b1661612242a23d0a8491139d
+size 5108961149

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a26687a1faa23062868a6a7e66f5010934ab32efbe7a11fa0fc3221e7f1b7ec
+size 5108961215

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e45870e3d4b28b02f22aae29da2ecd1b5764e786552cf58499c7dfa2b637cb
+size 5108961278

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92fe04dc043e4bd0c925ab868ac7879a7bd5f5e3af05d8eaf73093c9670e361c
+size 5108961309

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4e6b032daa3a6d6d63d11d491af4a904367ee123bbdc9e39ddfef9050a1925
+size 5108961301