XORTRON.CriminalComputing.LARGE.2026.3 — Hardware Requirements & GPU Compatibility
Chat
XORTRON.CriminalComputing.LARGE.2026.3 is a 122.6B-parameter open language model from darkc0de. It supports a context window of up to 131,072 tokens. At BF16 it needs about 246.26 GB of VRAM — see which GPUs and Macs can run it below.
441 downloads
46 likesSpecifications
- Publisher
- darkc0de
- Parameters
- 122.6B
- Architecture
- MistralForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 32,768
- Release Date
- 2026-03-01
- License
- WTFPL
Get Started
How Much VRAM Does XORTRON.CriminalComputing.LARGE.2026.3 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 246.3 GB | 292.8 GB | 245.22 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run XORTRON.CriminalComputing.LARGE.2026.3?
BF16 · 246.3 GBXORTRON.CriminalComputing.LARGE.2026.3 (BF16) requires 246.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 321+ GB is recommended. Using the full 131K context window can add up to 46.5 GB, bringing total usage to 292.8 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run XORTRON.CriminalComputing.LARGE.2026.3?
BF16 · 246.3 GB2 devices with unified memory can run XORTRON.CriminalComputing.LARGE.2026.3, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does XORTRON.CriminalComputing.LARGE.2026.3 need?
XORTRON.CriminalComputing.LARGE.2026.3 requires 246.3 GB of VRAM at BF16. Full 131K context adds up to 46.5 GB (292.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 122.6B × 16 bits ÷ 8 = 245.2 GB
KV Cache + Overhead ≈ 1.1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 47.6 GB (at full 131K context)
VRAM usage by quantization
BF16246.3 GBBF16 + full context292.8 GB- Can NVIDIA GeForce RTX 5090 run XORTRON.CriminalComputing.LARGE.2026.3?
No — XORTRON.CriminalComputing.LARGE.2026.3 requires at least 246.3 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run XORTRON.CriminalComputing.LARGE.2026.3 on a Mac?
XORTRON.CriminalComputing.LARGE.2026.3 requires at least 246.3 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run XORTRON.CriminalComputing.LARGE.2026.3 locally?
Yes — XORTRON.CriminalComputing.LARGE.2026.3 can run locally on consumer hardware. At BF16 quantization it needs 246.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of XORTRON.CriminalComputing.LARGE.2026.3?
At BF16, the download is about 245.22 GB.
- Which GPUs can run XORTRON.CriminalComputing.LARGE.2026.3?
No single consumer GPU has enough VRAM to run XORTRON.CriminalComputing.LARGE.2026.3 at BF16 (246.3 GB). Multi-GPU or professional hardware is required.
- Which devices can run XORTRON.CriminalComputing.LARGE.2026.3?
2 devices with unified memory can run XORTRON.CriminalComputing.LARGE.2026.3 at BF16 (246.3 GB), including NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.