QW

Qwen3.8 2B

QwenGGUF by empero-aiUpdated 2026-08-16
Download on Hugging Face
Parameters1.94B
Context256K
Layers25
Architectureqwen35
Smallest quant1.3 GB
Quick answer

Qwen3.8 2B needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.3 GB (Q4_K_M) to 3.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

Qwen3.8-2B: a distilled 2B‑parameter reasoning model with 262,144‑token context

Qwen3.8-2B is a full‑parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5‑2B architecture. It retains the same chain‑of‑thought curriculum and native 262,144‑token context. The model is released under Apache‑2.0 and supports function calling.

Good at

  • Chain‑of‑thought reasoning
  • Long‑context text generation
  • Instruction following

Limits

  • No vision support
  • Requires recent llama.cpp with Qwen3.5 support
  • Large memory at long context

Best for

  • Edge devices with limited VRAM
  • CPU‑only inference
  • Rapid prototyping of reasoning agents

Who it’s for. Developers and researchers needing a compact, reasoning‑capable LLM for edge or CPU deployment. The model is suitable for applications that require long‑context handling and native function calling without additional fine‑tuning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.3 GB 2.2 GB
Fits Get file →
Q5_K_M1.5 GB 2.4 GB
Fits Get file →
Q6_K1.6 GB 2.5 GB
Fits Get file →
Q8_02.1 GB 3.0 GB
Fits Get file →
BF163.9 GB 4.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.31 GB, ~2.2 GB memory at 8 k context). If 12 GB VRAM is available, Q5_K_M (1.45 GB, ~2.4 GB memory) offers a balance of quality and size. For maximum quality on 16 GB VRAM, Q8_0 (2.08 GB, ~3 GB memory) is recommended.

What GPU do you need for Qwen3.8 2B?

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 Q8_0 (2.1 GB file, about 3.0 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (3.9 GB file, about 4.8 GB in use).

Which Qwen3.8 2B quant should you choose?

Q4_K_M is the usual starting point for Qwen3.8 2B: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.1 GB, about 1.6 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
Parameters1.94B
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized byempero-ai
FamilyQwen
Licenseapache-2.0
Downloads (HF)479,711
Last updated2026-08-16

Frequently asked questions about Qwen3.8 2B

How much VRAM does Qwen3.8 2B need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Qwen3.8 2B on an 8 GB GPU?

Yes, with BF16: the 3.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.8 2B GGUF?

It depends on the quant: Q4_K_M is 1.3 GB, Q5_K_M is 1.5 GB, Q6_K is 1.6 GB, Q8_0 is 2.1 GB, BF16 is 3.9 GB.

What context length does Qwen3.8 2B 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 1.7 GB at 32K.

Where can I download Qwen3.8 2B GGUF?

The files are on Hugging Face in the empero-ai/Qwen3.8-2B-Distill-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 Qwen3.8 2B 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 Qwen3.8-2B on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 2.2 GB memory at 8 k context, fitting comfortably in 8 GB VRAM.

Does this model support vision tasks?

No, Qwen3.8-2B is a text‑only model 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 Qwen3.8-2B-Distill

Similar models

Browse all →

More from empero-ai

All by empero-ai →

More Qwen models

All Qwen →

Other tiny models

All tiny models →