AR

arco reasoner v1.3

ArcoGGUF by mradermacherUpdated 2024-09-15
Download on Hugging Face
Parameters514M
Context8K
Layers16
Architecturellama
Smallest quant0.2 GB
Quick answer

arco reasoner v1.3 needs about 1.2 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.2 GB (Q2_K) to 1.0 GB (F16).

arco reasoner v1.3 – a 514M llama model fine‑tuned for reasoning

arco reasoner v1.3 is a 514 billion‑parameter llama model fine‑tuned from arco‑interpreter‑v1.2. It supports a 8192‑token context window and is released under the apache‑2.0 license. The model is available in multiple static quantizations.

Good at

  • Reasoning tasks
  • Long‑context handling
  • Low‑memory inference

Limits

  • No vision support
  • No mixture‑of‑experts
  • Requires 8 k context for estimates

Best for

  • Chatbots needing reasoning
  • Document summarization with long context
  • Code explanation

Who it’s for. Developers and researchers who need a lightweight reasoning model with a large context window. The model is suitable for local deployment on machines with modest GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB 1.1 GB
Fits Get file →
IQ3_XS0.2 GB 1.1 GB
Fits Get file →
IQ3_S0.2 GB 1.1 GB
Fits Get file →
Q3_K_S0.2 GB 1.1 GB
Fits Get file →
IQ3_M0.2 GB 1.2 GB
Fits Get file →
Q3_K_M0.3 GB 1.2 GB
Fits Get file →
Q3_K_L0.3 GB 1.2 GB
Fits Get file →
IQ4_XS0.3 GB 1.2 GB
Fits Get file →
Q4_K_S0.3 GB 1.2 GB
Fits Get file →
Q4_K_M0.3 GB 1.2 GB
Fits Get file →
Q5_K_S0.4 GB 1.3 GB
Fits Get file →
Q5_K_M0.4 GB 1.3 GB
Fits Get file →
Q6_K0.4 GB 1.3 GB
Fits Get file →
Q8_00.5 GB 1.4 GB
Fits Get file →
F161.0 GB 1.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M or Q5_K_M (file sizes 0.32 GB and 0.37 GB, memory estimates 1.2 GB and 1.3 GB). For tighter budgets, Q2_K or IQ3_XS (0.21 GB and 0.23 GB, 1.1 GB memory). Higher precision can be achieved with Q8_0 or F16 if memory allows.

What GPU do you need for arco reasoner v1.3?

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 F16 (1.0 GB file, about 1.9 GB in use).

Which arco reasoner v1.3 quant should you choose?

Q4_K_M is the usual starting point for arco reasoner v1.3: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.2 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

Architecturellama
Parameters514M
Layers16
Trained context8,192 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilyArco
Licenseapache-2.0
Downloads (HF)610
Last updated2024-09-15

Frequently asked questions about arco reasoner v1.3

How much VRAM does arco reasoner v1.3 need?

About 1.2 GB at Q4_K_M with an 8K context window. That is the 0.3 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 arco reasoner v1.3 on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of arco reasoner v1.3 GGUF?

It depends on the quant: Q2_K is 0.2 GB, IQ3_XS is 0.2 GB, IQ3_S is 0.2 GB, Q3_K_S is 0.2 GB, IQ3_M is 0.2 GB, Q3_K_M is 0.3 GB and 9 more.

What context length does arco reasoner v1.3 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.4 GB at 8K.

Where can I download arco reasoner v1.3 GGUF?

The files are on Hugging Face in the mradermacher/arco-reasoner-v1.3-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 arco reasoner v1.3 use?

Hugging Face lists the license as apache-2.0. 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 arco reasoner v1.3 on 8 GB VRAM?

Yes, quantizations such as Q4_K_M or Q5_K_M fit within 8 GB VRAM with memory estimates around 1.2–1.3 GB.

Does the model support vision?

No, arco reasoner v1.3 does not include vision capabilities.

What license does the model use?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Arco models

All Arco →

Other tiny models

All tiny models →