Open-weight model
EryriLabs-Ornith-1.5-35B-A3B-BigBang-MTP-MTPLX
by Eric Peters epetersio/EryriLabs-Ornith-1.5-35B-A3B-BigBang-MTP-MTPLX
EryriLabs-Ornith-1.5-35B-A3B-BigBang-MTP-MTPLX is an open-weight model from Eric Peters. It has 35.1B parameters and a 262,144-token context. At 16-bit it needs about 84.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
MTPLX-branded multi-token-prediction model for Apple Silicon (MLX). Forged with MTPLX Forge from EryriLabs/Ornith-1.5-35B-A3B-BigBang-MTP. See mtplxruntime.json for the full verification record. See LICENSE.
Runs On
What it takes to serve EryriLabs-Ornith-1.5-35B-A3B-BigBang-MTP-MTPLX (35.1B 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 | 70.2 GB | 84.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x MI325X $2.00 · 1x MI355X $2.59 |
| 8-bit | 35.1 GB | 42.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 17.6 GB | 21.1 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 19, 2026.
Model Card
MTPLX-branded multi-token-prediction model for Apple Silicon (MLX). Forged with MTPLX Forge from EryriLabs/Ornith-1.5-35B-A3B-BigBang-MTP. See mtplxruntime.json for the full verification record. See LICENSE.
Excerpt from the card by Eric Peters.
Configuration
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 40
- Hidden size
- 2,048
- Attention heads
- 16
- Key/value heads
- 2
- Head dimension
- 256
- Vocabulary size
- 248,320
- Experts
- 256
- Experts active per token
- 8
- Model type
- qwen3_5_moe
Identity and Version
- Repository
- epetersio/EryriLabs-Ornith-1.5-35B-A3B-BigBang-MTP-MTPLX
- Publisher
- Eric Peters
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 35.1B parameters
- Languages
- Not stated by the source
- Revision
- b4b651af970bde631b8c167d9c29c2bb29438ad2
- First published
- 2026-09-23
- Last updated
- 2026-09-24
Files and Weights
18 files, 22.1 GB in total. The weights are 6 files totalling 22.1 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00004.safetensors | Weights | 5.3 GB | 31a5ff844f2b |
| model-00002-of-00004.safetensors | Weights | 5.4 GB | e0a72ce9df0d |
| model-00003-of-00004.safetensors | Weights | 5.4 GB | 22a6fb2cd6cc |
| model-00004-of-00004.safetensors | Weights | 3.4 GB | 89a2d3156591 |
| model-vision.safetensors | Weights | 893.2 MB | 0b8aec604ebd |
| mtp.safetensors | Weights | 1.7 GB | cb1dd3f1475c |
| config.json | Configuration | 20.5 KB | — |
| generation_config.json | Configuration | 202 B | — |
| model.safetensors.index.json | Configuration | 204.8 KB | — |
| mtplx_runtime.json | Configuration | 4.0 KB | — |
| preprocessor_config.json | Configuration | 390 B | — |
| processor_config.json | Configuration | 1.2 KB | — |
| video_preprocessor_config.json | Configuration | 385 B | — |
| README.md | Documentation | 643 B | — |
| chat_template.jinja | Other | 7.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 28.1 MB | 697dcad33c4c |
| tokenizer_config.json | Tokenizer | 1.2 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 22.1 GB
Released by Eric Peters through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 22.1 GB |
| 16-bit | 70.2 GB |
| 8-bit | 35.1 GB |
| 4-bit | 17.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About EryriLabs-Ornith-1.5-35B-A3B-BigBang-MTP-MTPLX
How much GPU memory does EryriLabs-Ornith-1.5-35B-A3B-BigBang-MTP-MTPLX need?
About 84.3 GB at 16-bit and 21.1 GB at 4-bit: the weights (35.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run EryriLabs-Ornith-1.5-35B-A3B-BigBang-MTP-MTPLX 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 is EryriLabs-Ornith-1.5-35B-A3B-BigBang-MTP-MTPLX's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.