MLX 6-bit weights with group size 64; a 3.732 GB weight package. Fixed memory for long-running generation. This EdgeRock-4B deployment package retains recurrent state, local attention, and Rock Memory Anchors (RMA), keeping persistent history at a fixed capacity as context grows. 固定记忆，长程生成。 本版本保留 EdgeRock-4B 的递推状态、局部注意力和记忆岩锚（RMA），历史内存不随上下文增长。 Rock Matrix Whitepaper / 岩芯矩阵技术白皮书： whitepaper connects EdgeRock's fixed memory, DiffusionRock's parallel generation, and SiliconRock's model-native silicon into the route toward Ultra-Fast Token. 白皮书讲清固定记忆、并行生成、模型固化三条路线，以及它们如何走向更快、更经济的生成。 The instructions and validation below apply to this package. Browse all EdgeRock models. Original-model benchmarks…
EdgeRock-4B-AWQ is an open-weight model for text generation from Aaron Xu, released under other. It has 4.6B parameters and a 262,144-token context. At 16-bit it needs about 11 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 32 downloads a month.
AWQ W4A16 weights for Rock Matrix's EdgeRock-4B, with a packed INT4 CUDA runtime. Fixed memory for long-running generation.
Parameters4.6B
Context262,144
Weights3.4 GB
Licenseother
AccessOpen weights
Monthly Downloads32
Runs On
What it takes to serve EdgeRock-4B-AWQ (4.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 9.2 GB | 11.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.6 GB | 5.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.3 GB | 2.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 23, 2026.
EdgeRock-4B-AWQ on every accelerator the SAVRN Index prices, at every precision
Model Card
AWQ W4A16 weights for Rock Matrix's EdgeRock-4B, with a packed INT4 CUDA runtime. Fixed memory for long-running generation. This EdgeRock-4B deployment package retains recurrent state, local attention, and Rock Memory Anchors (RMA), keeping persistent history at a fixed capacity as context grows. 固定记忆，长程生成。 本版本保留 EdgeRock-4B 的递推状态、局部注意力和记忆岩锚（RMA），历史内存不随上下文增长。 Rock Matrix Whitepaper / 岩芯矩阵技术白皮书： whitepaper connects EdgeRock's fixed memory, DiffusionRock's parallel generation, and SiliconRock's model-native silicon into the route toward Ultra-Fast Token. 白皮书讲清固定记忆、并行生成、模型固化三条路线，以及它们如何走向更快、更经济的生成。 EdgeRock combines recurrent state, sliding-window attention and Rock Memory Anchors (RMA) to…
Excerpt from the card by Aaron Xu, licensed other.
Configuration
- Architecture
- EdgeRockForCausalLM
- Context length (tokens)
- 262,144
- Layers
- 32
- Hidden size
- 2,560
- Feed-forward size
- 9,216
- Attention heads
- 16
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 248,320
- Model type
- edgerock
- Quantization
- awq
Identity and Version
- Repository
- hkust-aaron/EdgeRock-4B-AWQ
- Publisher
- Aaron Xu
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 4.6B parameters
- Languages
- en, zh
- Revision
- e9e6b5f945282ed17f54efc300b194b9b4c9164b
- First published
- 2026-10-19
- Last updated
- 2026-10-23
Files and Weights
27 files, 3.4 GB in total. The weights are 3 files totalling 3.4 GB in pt, safetensors.
Weights3 files · 3.4 GB
Configuration13 files · 282.3 KB
Tokenizer2 files · 20.0 MB
Documentation4 files · 39.1 KB
Other4 files · 2.6 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00002.safetensors | Weights | 2.1 GB | e3a0e8498bca |
| model-00002-of-00002.safetensors | Weights | 1.3 GB | 448d175c6128 |
| reference_probe.pt | Weights | 994.9 KB | a43572853382 |
| calibration.json | Configuration | 1.9 KB | — |
| config.json | Configuration | 2.8 KB | — |
| configuration_edgerock.py | Configuration | 945 B | — |
| conversion.json | Configuration | 10.2 KB | — |
| edgerock_quantization.json | Configuration | 38.3 KB | — |
| generation_config.json | Configuration | 168 B | — |
| model.safetensors.index.json | Configuration | 110.7 KB | — |
| modeling_edgerock.py | Configuration | 67.6 KB | — |
| packed_int4.py | Configuration | 6.1 KB | — |
| provenance.json | Configuration | 4.8 KB | — |
| quantize.py | Configuration | 8.2 KB | — |
| validate.py | Configuration | 5.2 KB | — |
| validation.json | Configuration | 25.3 KB | — |
| LICENSE | Documentation | 18.0 KB | — |
| LICENSE-CODE | Documentation | 11.4 KB | — |
| NOTICE | Documentation | 3.6 KB | — |
| README.md | Documentation | 6.1 KB | — |
| SHA256SUMS | Other | 2.1 KB | — |
| chat_template.jinja | Other | 217 B | — |
| requirements-conversion.txt | Other | 58 B | — |
| requirements.txt | Other | 241 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | 06b9509352d2 |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 3.4 GB
Download from Aaron Xu
Released by Aaron Xu through its official repository on Hugging Face.
Built From
- Derived from rockmatrix-ai/EdgeRock
- Described by arXiv:2610.10118
- Quantized from rockmatrix-ai/EdgeRock
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.4 GB |
| 16-bit | 9.2 GB |
| 8-bit | 4.6 GB |
| 4-bit | 2.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About EdgeRock-4B-AWQ
How much GPU memory does EdgeRock-4B-AWQ need?
About 11 GB at 16-bit and 2.7 GB at 4-bit: the weights (4.6B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run EdgeRock-4B-AWQ on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What license is EdgeRock-4B-AWQ released under?
other, as its publisher declares it. Read the license text before commercial use.
What is EdgeRock-4B-AWQ's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.
Similar Models
MLX 4-bit weights with group size 32; a 2.875 GB weight package. Fixed memory for long-running generation. This EdgeRock-4B deployment package retains recurrent state, local attention, and Rock Memory Anchors (RMA), keeping persistent history at a fixed capacity as context grows. 固定记忆，长程生成。 本版本保留 EdgeRock-4B 的递推状态、局部注意力和记忆岩锚（RMA），历史内存不随上下文增长。 Rock Matrix Whitepaper / 岩芯矩阵技术白皮书： whitepaper connects EdgeRock's fixed memory, DiffusionRock's parallel generation, and SiliconRock's model-native silicon into the route toward Ultra-Fast Token. 白皮书讲清固定记忆、并行生成、模型固化三条路线，以及它们如何走向更快、更经济的生成。 The instructions and validation below apply to this package. Browse all EdgeRock models. Original-model benchmarks…
MLX 8-bit weights with group size 64; a 4.874 GB weight package. Fixed memory for long-running generation. This EdgeRock-4B deployment package retains recurrent state, local attention, and Rock Memory Anchors (RMA), keeping persistent history at a fixed capacity as context grows. 固定记忆，长程生成。 本版本保留 EdgeRock-4B 的递推状态、局部注意力和记忆岩锚（RMA），历史内存不随上下文增长。 Rock Matrix Whitepaper / 岩芯矩阵技术白皮书： whitepaper connects EdgeRock's fixed memory, DiffusionRock's parallel generation, and SiliconRock's model-native silicon into the route toward Ultra-Fast Token. 白皮书讲清固定记忆、并行生成、模型固化三条路线，以及它们如何走向更快、更经济的生成。 The instructions and validation below apply to this package. Browse all EdgeRock models. Original-model benchmarks…
MLX mixed precision: 4-bit MLPs and 8-bit other eligible matrices, with group size 64; 3.741 GB of weights. Fixed memory for long-running generation. This EdgeRock-4B deployment package retains recurrent state, local attention, and Rock Memory Anchors (RMA), keeping persistent history at a fixed capacity as context grows. 固定记忆，长程生成。 本版本保留 EdgeRock-4B 的递推状态、局部注意力和记忆岩锚（RMA），历史内存不随上下文增长。 Rock Matrix Whitepaper / 岩芯矩阵技术白皮书： whitepaper connects EdgeRock's fixed memory, DiffusionRock's parallel generation, and SiliconRock's model-native silicon into the route toward Ultra-Fast Token. 白皮书讲清固定记忆、并行生成、模型固化三条路线，以及它们如何走向更快、更经济的生成。 The instructions and validation below apply to this package. Browse all…
GPTQ W4A16 weights for Rock Matrix's EdgeRock-4B, with a packed INT4 CUDA runtime. Fixed memory for long-running generation. This EdgeRock-4B deployment package retains recurrent state, local attention, and Rock Memory Anchors (RMA), keeping persistent history at a fixed capacity as context grows. 固定记忆，长程生成。 本版本保留 EdgeRock-4B 的递推状态、局部注意力和记忆岩锚（RMA），历史内存不随上下文增长。 Rock Matrix Whitepaper / 岩芯矩阵技术白皮书： whitepaper connects EdgeRock's fixed memory, DiffusionRock's parallel generation, and SiliconRock's model-native silicon into the route toward Ultra-Fast Token. 白皮书讲清固定记忆、并行生成、模型固化三条路线，以及它们如何走向更快、更经济的生成。 EdgeRock combines recurrent state, sliding-window attention and Rock Memory Anchors (RMA) to…
YANchor-4B is a general-purpose recurrent model that preserves crucial memory as ANchors for retrieval during subsequent reasoning. Its multidimensional memory mechanism enables effective long-horizon reasoning with O(N) generation time and O(1) history-state memory. For example, on challenging math problems, YANchor achieves 82.93% mean pass@1 on AIME 2024–2026 and 63.64% on HMMT, substantially outperforming linear-time, constant-state counterparts, including 7B–14B models. YANchor delivers several-fold higher batched long-generation throughput than Transformer and hybrid baselines on H100. Evaluations across dozens of benchmarks demonstrate its superiority in general-purpose capabilities.…