QW

qwen3loop 0.6b tool calling sft v1

QwenGGUF by LordnyxUpdated 2026-09-28
Download on Hugging Face
Parameters596M
Context40K
Layers—
Architectureqwen3
Smallest quant0.6 GB
Quick answer

qwen3loop 0.6b tool calling sft v1 needs about 1.7 GB of memory at Q8_0 (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.6 GB (Q8_0) to 2.1 GB (F16).

Qwen3Loop‑0.6B Tool‑Calling SFT – narrow tool‑calling specialist

Qwen3Loop‑0.6B Tool‑Calling SFT is a 0.6B‑parameter recurrent Qwen3Loop model fine‑tuned on 2,498 strict tool‑calling samples. It supports single‑turn user→assistant(tool_calls) interactions and mid‑trajectory corrections. The model is trained on English data and uses a 40,960‑token context window.

Good at

  • Tool‑calling in single‑turn interactions
  • Mid‑trajectory corrections
  • Python execution via execute_python

Limits

  • English only
  • Abstention unstable (12/20 success)
  • No vision support

Best for

  • Automated code execution tasks
  • API‑driven workflows
  • Finance‑related tool calls

Who it’s for. Developers building narrow agents that need reliable tool invocation in English. The model is suitable for environments where tool calls have cost or side effects and external gating is acceptable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.6 GB 1.2 GB
Fits Get file →
Q8_01.1 GB 1.7 GB
Fits Get file →
F161.2 GB 1.8 GB
Fits Get file →
F162.1 GB 2.8 GB
Fits Get file →

For 8 GB VRAM, use the Q8_0 quant with 0.64 GB file size, which requires about 1.2 GB memory at 8 k context. For 12 GB VRAM, the 1.11 GB Q8_0 file needs about 1.7 GB memory. Larger VRAM allows the 1.2 GB F16 or 2.08 GB F16 variants with 1.8 GB or 2.8 GB memory respectively.

What GPU do you need for qwen3loop 0.6b tool calling sft v1?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (2.1 GB file, about 2.8 GB in use).

Which qwen3loop 0.6b tool calling sft v1 quant should you choose?

Q8_0 (1.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q8_0 at 0.6 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters596M
Trained context40,960 tokens

Source

Quantized byLordnyx
FamilyQwen
Licenseapache-2.0
Downloads (HF)777
Last updated2026-09-28

Frequently asked questions about qwen3loop 0.6b tool calling sft v1

How much VRAM does qwen3loop 0.6b tool calling sft v1 need?

About 1.7 GB at Q8_0 with an 8K context window. That is the 1.1 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 qwen3loop 0.6b tool calling sft v1 on an 8 GB GPU?

Yes, with F16: the 2.1 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of qwen3loop 0.6b tool calling sft v1 GGUF?

It depends on the quant: Q8_0 is 0.6 GB, Q8_0 is 1.1 GB, F16 is 1.2 GB, F16 is 2.1 GB.

What context length does qwen3loop 0.6b tool calling sft v1 support?

The GGUF header lists a trained context length of 40,960 tokens (40K).

Where can I download qwen3loop 0.6b tool calling sft v1 GGUF?

The files are on Hugging Face in the Lordnyx/qwen3loop-0.6b-tool-calling-sft-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does qwen3loop 0.6b tool calling sft v1 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 0.64 GB Q8_0 quant requires about 1.2 GB memory at 8 k context, fitting comfortably on 8 GB VRAM.

Does it support non‑English prompts?

No, the model is trained almost exclusively on English and performs poorly on other languages.

Is the model suitable for multi‑turn conversations?

It supports multi‑turn correction but is primarily designed for single‑turn tool‑calling interactions.

Similar models

Browse all →

More from Lordnyx

All by Lordnyx →

More Qwen models

All Qwen →

Other tiny models

All tiny models →