QW

Qweling3.5 0.8B

QwelingGGUF by constructaiUpdated 2026-05-03
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.4 GB
Quick answer

Qweling3.5 0.8B needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.4 GB (Q2_K) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Qweling3.5 0.8B – a small, step‑by‑step reasoning model

Qweling3.5 0.8B is a 0.752 billion‑parameter model built on the qwen35 architecture. It is optimized for step‑by‑step reasoning tasks and runs efficiently on mobile or CPU‑only devices. The model is released under the apache‑2.0 license.

Good at

  • Educational reasoning
  • On‑device assistants
  • Fast prototyping

Limits

  • No multimodal support
  • May hallucinate on complex queries
  • Optimized for T4/consumer GPUs

Best for

  • Explaining math steps
  • Teaching science concepts
  • Research on reasoning distillation

Who it’s for. Developers needing a lightweight reasoning model for mobile or embedded applications. Researchers studying SFT‑only reasoning or distillation experiments may also benefit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.3 GB
Fits Get file →
Q3_K_S0.4 GB 1.3 GB
Fits Get file →
Q3_K_M0.5 GB 1.4 GB
Fits Get file →
Q3_K_L0.5 GB 1.4 GB
Fits Get file →
Q4_K_S0.5 GB 1.4 GB
Fits Get file →
IQ4_XS0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q5_K_S0.6 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →
F161.5 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M or Q4_K_S (0.53 GB or 0.51 GB) provide a good balance of size and memory usage. If memory is tighter, Q3_K_M (0.47 GB) or Q3_K_S (0.44 GB) are suitable. Higher precision F16 (1.52 GB) requires more VRAM but offers better accuracy.

What GPU do you need for Qweling3.5 0.8B?

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 (1.5 GB file, about 2.4 GB in use).

Which Qweling3.5 0.8B quant should you choose?

Q4_K_M is the usual starting point for Qweling3.5 0.8B: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.5 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 0.4 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

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byconstructai
FamilyQweling
Licenseapache-2.0
Downloads (HF)636
Last updated2026-05-03

Frequently asked questions about Qweling3.5 0.8B

How much VRAM does Qweling3.5 0.8B need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 Qweling3.5 0.8B on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qweling3.5 0.8B GGUF?

It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_K_S is 0.5 GB, IQ4_XS is 0.5 GB and 6 more.

What context length does Qweling3.5 0.8B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Qweling3.5 0.8B GGUF?

The files are on Hugging Face in the constructai/Qweling3.5-0.8B-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 Qweling3.5 0.8B 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 Qweling3.5 0.8B on 8 GB VRAM?

Yes, quantized versions such as Q4_K_M or Q4_K_S fit comfortably within 8 GB VRAM.

Does the model support image input?

No, the model is text‑only and does not support multimodal input.

Is the model safe for production use?

The model may hallucinate and is not safety‑filtered; it is not recommended for production systems requiring 100% factual accuracy.

Other GGUFs of Qweling3.5-0.8B

Similar models

Browse all →

More from constructai

All by constructai →

More Qweling models

All Qweling →

Other tiny models

All tiny models →