QW

smol tools 4b 32k

QwenGGUF by enfuseUpdated 2026-03-18
Download on Hugging Face
Parameters4.84B
Context256K
Layers32
Architectureqwen35
Smallest quant3.1 GB
Quick answer

smol tools 4b 32k needs about 4.6 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.1 GB (Q4_K_M) to 5.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

4B parameter Qwen model with 32K context and tool‑use focus

smol tools 4b 32k is a 4.84B parameter Qwen model fine‑tuned for reliable tool calling. It supports 32K token context and is built on Qwen3.5‑4B-Claude‑4.6‑Opus‑Reasoning‑Distilled. The model is text‑only and uses hybrid attention for efficient long‑context inference.

Good at

  • Long‑context tool‑use
  • Multi‑turn agent workflows
  • JSON‑valid tool calls

Limits

  • No vision support
  • Requires 32K context for full capability
  • Apache‑2.0 license

Best for

  • Agentic workflows with many tool calls
  • Long document analysis with tool calls
  • Complex multi‑step reasoning

Who it’s for. Developers building agentic applications that need extended context and accurate tool usage. Researchers testing long‑context reasoning in a lightweight model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M3.1 GB 4.6 GB
Fits Get file →
Q8_05.2 GB 6.7 GB
Fits Get file →

For 8‑GB VRAM, use the Q4_K_M quant (3.07 GB file, ~4.6 GB memory at 8K context). If you have 12‑GB VRAM, the Q8_0 quant (5.16 GB file, ~6.7 GB memory) offers higher precision. Memory estimates are approximate.

What GPU do you need for smol tools 4b 32k?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (3.1 GB file, about 4.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.2 GB file, about 6.7 GB in use).

Which smol tools 4b 32k quant should you choose?

Q4_K_M is the usual starting point for smol tools 4b 32k: it balances file size and quality well. Here it is a 3.1 GB file.

The Q8_0 file is 5.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.84B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byenfuse
FamilyQwen
Licenseapache-2.0
Downloads (HF)924
Last updated2026-03-18

Frequently asked questions about smol tools 4b 32k

How much VRAM does smol tools 4b 32k need?

About 4.6 GB at Q4_K_M with an 8K context window. That is the 3.1 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 smol tools 4b 32k on an 8 GB GPU?

Yes, with Q8_0: the 5.2 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of smol tools 4b 32k GGUF?

It depends on the quant: Q4_K_M is 3.1 GB, Q8_0 is 5.2 GB.

What context length does smol tools 4b 32k support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download smol tools 4b 32k GGUF?

The files are on Hugging Face in the enfuse/smol-tools-4b-32k repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does smol tools 4b 32k 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 smol tools 4b 32k on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 4.6 GB of VRAM at 8K context, fitting within 8 GB.

Does this model support vision?

No, the model is text‑only and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled

Similar models

Browse all →

More from enfuse

All by enfuse →

More Qwen models

All Qwen →

Other small models

All small models →