LL

Llama 3.2 3B claude 3.7 sonnet reasoning distilled

LlamaGGUF by mfielding92Updated 2026-06-05
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant1.9 GB
Quick answer

Llama 3.2 3B claude 3.7 sonnet reasoning distilled needs about 3.4 GB of memory at Q4_0 (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.9 GB (Q4_0) to 3.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama 3.2 3B fine‑tuned for reasoning with Claude 3.7 Sonnet data

This model is a Llama 3.2 3B Instruct variant fine‑tuned with reasoning data from Claude 3.7 Sonnet. It aims to bring advanced logical thinking to an open‑source architecture. The model is released under the Apache‑2.0 license.

Good at

  • Reasoning
  • Tool use
  • Logical problem solving

Limits

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

Best for

  • Complex reasoning tasks
  • Tool‑enabled workflows
  • Educational tutoring

Who it’s for. Developers and researchers who need a lightweight, reasoning‑capable LLM for local deployment. The model is suitable for projects that require open‑source licensing and moderate GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.9 GB 3.4 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →

For 8 GB VRAM, use the Q4_0 quantized file (1.92 GB, ~3.4 GB memory at 8k context). For 12 GB VRAM, the Q8_0 file (3.42 GB, ~4.9 GB memory) provides higher precision. Memory estimates are approximate.

What GPU do you need for Llama 3.2 3B claude 3.7 sonnet reasoning distilled?

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 Q4_0 (1.9 GB file, about 3.4 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).

Which Llama 3.2 3B claude 3.7 sonnet reasoning distilled quant should you choose?

Q4_0 (1.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymfielding92
FamilyLlama
Licenseapache-2.0
Downloads (HF)613
Last updated2026-06-05

Frequently asked questions about Llama 3.2 3B claude 3.7 sonnet reasoning distilled

How much VRAM does Llama 3.2 3B claude 3.7 sonnet reasoning distilled need?

About 3.4 GB at Q4_0 with an 8K context window. That is the 1.9 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 Llama 3.2 3B claude 3.7 sonnet reasoning distilled on an 8 GB GPU?

Yes, with Q8_0: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.2 3B claude 3.7 sonnet reasoning distilled GGUF?

It depends on the quant: Q4_0 is 1.9 GB, Q8_0 is 3.4 GB.

What context length does Llama 3.2 3B claude 3.7 sonnet reasoning distilled support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Llama 3.2 3B claude 3.7 sonnet reasoning distilled GGUF?

The files are on Hugging Face in the mfielding92/Llama-3.2-3B-claude-3.7-sonnet-reasoning-distilled repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Llama 3.2 3B claude 3.7 sonnet reasoning distilled 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 this model on 8 GB VRAM?

Yes, the Q4_0 quantized file is 1.92 GB and requires about 3.4 GB of VRAM at 8k context, fitting within an 8 GB GPU.

Does it support vision or image inputs?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache-2.0 license.

Similar models

Browse all →

More from mfielding92

All by mfielding92 →

More Llama models

All Llama →

Other tiny models

All tiny models →