Arch Router 1.5B — Hardware Requirements & GPU Compatibility
Chat
Arch Router 1.5B is a 1.5B-parameter open language model from katanemo. It supports a context window of up to 32,768 tokens. At FP16 it needs about 3.45 GB of VRAM — see which GPUs and Macs can run it below.
1.6K downloads
264 likesSpecifications
- Publisher
- katanemo
- Parameters
- 1.5B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-04-02
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Arch Router 1.5B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| FP16 | 16.00 | 3.5 GB | 4.3 GB | 3.09 GB | Full half-precision — baseline for inference |
Which GPUs Can Run Arch Router 1.5B?
FP16 · 3.5 GBArch Router 1.5B (FP16) requires 3.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. Using the full 33K context window can add up to 0.9 GB, bringing total usage to 4.3 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Arch Router 1.5B?
FP16 · 3.5 GB33 devices with unified memory can run Arch Router 1.5B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Arch Router 1.5B need?
Arch Router 1.5B requires 3.5 GB of VRAM at FP16. Full 33K context adds up to 0.9 GB (4.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.5B × 16 bits ÷ 8 = 3.1 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.2 GB (at full 33K context)
VRAM usage by quantization
FP163.5 GBFP16 + full context4.3 GB- Can I run Arch Router 1.5B on a Mac?
Arch Router 1.5B requires at least 3.5 GB at FP16, 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 Arch Router 1.5B locally?
Yes — Arch Router 1.5B can run locally on consumer hardware. At FP16 quantization it needs 3.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Arch Router 1.5B?
At FP16, Arch Router 1.5B can reach ~845 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~190 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 3.5 × 0.55 = ~845 tok/s
Estimated speed at FP16 (3.5 GB)
~845 tok/s~190 tok/s~632 tok/s~522 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Arch Router 1.5B?
At FP16, the download is about 3.09 GB.
- Which GPUs can run Arch Router 1.5B?
35 consumer GPUs can run Arch Router 1.5B at FP16 (3.5 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Arch Router 1.5B?
33 devices with unified memory can run Arch Router 1.5B at FP16 (3.5 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.