QW

Arch Router

QwenGGUF by katanemoUpdated 2026-04-02
Download on Hugging Face
Parameters1.54B
Context32K
Layers28
Architectureqwen2
Smallest quant0.7 GB
Quick answer

Arch Router needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 0.7 GB (Q2_K) to 3.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Arch Router: 1.5B Qwen2.5 model for preference‑based routing

Arch Router is a 1.5B parameter Qwen2.5 instruction‑tuned model. It maps user queries to domain and action preferences for routing decisions. The model supports a full 32,768 token context and generates up to 8,192 tokens.

Good at

  • Routing queries to domain‑action pairs
  • Instruction following
  • Long‑context generation

Limits

  • No vision support
  • License is other
  • No multilingual details beyond base

Best for

  • Agent routing systems
  • Preference‑based chatbot backends
  • Domain‑specific model selection

Who it’s for. Developers building AI‑native proxies or agents that need to route user requests to appropriate models. The model is useful for systems requiring quick domain and action inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.7 GB 1.4 GB
Fits Get file →
Q3_K_S0.8 GB 1.5 GB
Fits Get file →
Q3_K_M0.8 GB 1.6 GB
Fits Get file →
Q3_K_L0.9 GB 1.6 GB
Fits Get file →
Q4_K_S0.9 GB 1.7 GB
Fits Get file →
Q4_K_M1.0 GB 1.7 GB
Fits Get file →
Q5_K_S1.1 GB 1.8 GB
Fits Get file →
Q5_K_M1.1 GB 1.9 GB
Fits Get file →
Q6_K1.3 GB 2.0 GB
Fits Get file →
—3.1 GB 3.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 0.99 GB, estimated memory 1.7 GB). For 4 GB VRAM, use Q3_K_S (0.76 GB, 1.5 GB). For 2 GB VRAM, use Q2_K (0.68 GB, 1.4 GB).

What GPU do you need for Arch Router?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (3.1 GB file, about 3.8 GB in use).

Which Arch Router quant should you choose?

Q4_K_M is the usual starting point for Arch Router: it balances file size and quality well. Here it is a 1.0 GB file.

If memory is tight, the smallest file is Q2_K at 0.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters1.54B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized bykatanemo
FamilyQwen
Licenseother
Downloads (HF)1,457
Last updated2026-04-02

Frequently asked questions about Arch Router

How much VRAM does Arch Router need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Arch Router on an 8 GB GPU?

Yes, with the smaller files: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Arch Router GGUF?

It depends on the quant: Q2_K is 0.7 GB, Q3_K_S is 0.8 GB, Q3_K_M is 0.8 GB, Q3_K_L is 0.9 GB, Q4_K_S is 0.9 GB, Q4_K_M is 1.0 GB and 4 more.

What context length does Arch Router support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download Arch Router GGUF?

The files are on Hugging Face in the katanemo/Arch-Router-1.5B.gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Arch Router use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Arch Router on 8 GB VRAM?

Yes, the Q4_K_M quantized model requires about 1.7 GB of VRAM at 8 k context.

Does Arch Router support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports a full 32,768 token context and generates up to 8,192 tokens.

Other GGUFs of Qwen2.5-1.5B-Instruct

Similar models

Browse all →

More from katanemo

All by katanemo →

More Qwen models

All Qwen →

Other tiny models

All tiny models →