This model is a fine-tuned version of DuyTa/Cyber-F1. It has been trained using TRL. This model was trained with SFT. - PEFT 0.21.0
Open-weight model · Text generation
Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP
by Logic Gate thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP
Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP is an open-weight model for text generation from Logic Gate, released under Apache License 2.0. It has 35.1B parameters. 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.
Parameters35.1B
Context—
Weights—
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP (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 22, 2026.
Model Card
Identity and Version
- Repository
- thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP
- Publisher
- Logic Gate
- Task
- Text generation
- Modality
- Text
- Library
- mlx
- Parameters
- 35.1B parameters
- Languages
- mlx, moe, mtp
- Revision
- 95fc283fc522e97ef831c619bffd9a6c84cd9026
- First published
- 2026-10-21
- Last updated
- 2026-10-22
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
Download from Logic Gate
Released by Logic Gate through its official repository on Hugging Face. Read the license.
Built From
- Derived from InternScience/Sage-A1.5
- Quantized from InternScience/Sage-A1.5
- Trained on (disclosed) mlabonne/harmful_behaviors
- Trained on (disclosed) mlabonne/harmless_alpaca
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 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 Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP
How much GPU memory does Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP 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 Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP 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.
Can I use Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP commercially?
Yes. Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Internal research checkpoint. Routed experts average 2.0217 bits; every other weight is BF16. Weights are stored dequantized in BF16 tensors and load with stock transformers / vLLM. License follows the base model.
The abliterated version of Longleaf, our local model for coding, repository edits, debugging, and structured tools. - 35B total / 3B active parameters. - MLX 4-bit weights. - 262,144-token configured context. EvalPlus 0.3.1, 164 tasks, pass@1. Thinking off, greedy sampling, 2,048-token output cap, 262,144-token configured context. Generation used our M1 Ultra 231 / 198 / 195 tokens, respectively. CLI sample: five Terminal-Bench 2 tasks on ARM64, thinking off. Per task: 300 seconds, 24 model calls, 32 tool calls, 2,048 output tokens per call. Apache 2.0. This release contains modified model weights, based on Qwen3.6-35B-A3B, and the Abliteration changes refusal behavior, not output…
Longleaf is our local model for coding and agent work: repository edits, debugging, structured tools, and clear answers. Built on Qwen3.6-35B-A3B. - 35B total / 3B active parameters. - MLX 4-bit weights. - 262,144-token configured context. EvalPlus 0.3.1, 164 tasks, pass@1. Thinking off, greedy sampling, 2,048-token output cap, 262,144-token configured context. Generation used our M1 Ultra 231 / 198 / 195 tokens, respectively. CLI sample: five Terminal-Bench 2 tasks on ARM64, thinking off. Per task: 300 seconds, 24 model calls, 32 tool calls, 2,048 output tokens per call. Our M1 Ultra Splash runtime, medium thinking, model already loaded: Read, edit, and test completed in about 6 seconds…