AR

Arvi 20b

ArviGGUF by mradermacherUpdated 2025-12-21
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant0.0 GB
Quick answer

Arvi 20b needs about 16.7 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 22.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Arvi 20b – a 20‑billion‑parameter MoE reasoning model

Arvi 20b is a 20.9‑billion‑parameter Mixture‑of‑Experts model built on the gpt‑oss architecture. It supports long context up to 131072 tokens and is optimized for reasoning and tool usage. The model is released under Apache 2.0.

Good at

  • Long‑context reasoning
  • Tool‑aware agentic workflows
  • Chain‑of‑thought generation

Limits

  • Requires MoE backend kernels
  • No vision support
  • Large VRAM needed for full precision

Best for

  • Complex reasoning tasks
  • Autonomous tool‑calling systems
  • Large‑document analysis

Who it’s for. Developers and researchers needing a high‑capacity reasoning model that can be run on standard enterprise hardware with the right MoE support. The model is suitable for applications that require deep logical decomposition and tool integration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ1_M12.0 GB 12.9 GB
Too big Get file →
IQ1_S12.0 GB 12.9 GB
Too big Get file →
IQ2_XXS12.0 GB 12.9 GB
Too big Get file →
IQ2_XS12.0 GB 12.9 GB
Too big Get file →
Q3_K_S12.1 GB 13.0 GB
Too big Get file →
IQ2_M12.1 GB 13.0 GB
Too big Get file →
IQ2_S12.1 GB 13.0 GB
Too big Get file →
IQ3_S12.1 GB 13.0 GB
Too big Get file →
IQ3_XS12.1 GB 13.0 GB
Too big Get file →
IQ3_XXS12.1 GB 13.0 GB
Too big Get file →
Q2_K12.1 GB 13.0 GB
Too big Get file →
IQ4_XS12.1 GB 13.0 GB
Too big Get file →
Q2_K_S12.1 GB 13.0 GB
Too big Get file →
Q4_012.1 GB 13.1 GB
Too big Get file →
IQ3_M12.2 GB 13.1 GB
Too big Get file →
Q3_K_M12.9 GB 13.8 GB
Too big Get file →
Q3_K_L13.3 GB 14.2 GB
Too big Get file →
Q4_113.4 GB 14.3 GB
Too big Get file →
Q4_K_S14.7 GB 15.6 GB
Too big Get file →
Q4_K_M15.8 GB 16.7 GB
Too big Get file →
Q5_K_S15.9 GB 16.8 GB
Too big Get file →
Q5_K_M16.9 GB 17.8 GB
Too big Get file →
Q6_K22.2 GB 23.1 GB
Too big Get file →

For 8 GB VRAM, use the IQ1_M or IQ1_S quant (12.02 GB file, ~12.9 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (15.81 GB file, ~16.7 GB memory) or Q5_K_M (16.89 GB file, ~17.8 GB memory) are suitable. For larger budgets, Q6_K (22.19 GB file, ~23.1 GB memory) provides the highest fidelity.

What GPU do you need for Arvi 20b?

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 (0.0 GB file, about 0.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (14.7 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 23.1 GB in use).

Which Arvi 20b quant should you choose?

Q4_K_M is the usual starting point for Arvi 20b: it balances file size and quality well. Here it is a 15.8 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters20.9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilyArvi
Licenseapache-2.0
Downloads (HF)481
Last updated2025-12-21

Frequently asked questions about Arvi 20b

How much VRAM does Arvi 20b need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.8 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 Arvi 20b on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Arvi 20b GGUF?

It depends on the quant: file is 0.0 GB, IQ1_M is 12.0 GB, IQ1_S is 12.0 GB, IQ2_XXS is 12.0 GB, IQ2_XS is 12.0 GB, Q3_K_S is 12.1 GB and 18 more.

What context length does Arvi 20b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Arvi 20b GGUF?

The files are on Hugging Face in the mradermacher/arvi-20b-i1-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 Arvi 20b 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 Arvi 20b on 8 GB VRAM?

Use IQ1_M or IQ1_S quant; each requires about 12.9 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does Arvi 20b support vision?

No, the model has no vision capabilities.

Other GGUFs of arvi-20b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Arvi models

All Arvi →

Other medium models

All medium models →