QW

Qwen3.8 23B Mini Me Bf16

QwenGGUF by torchsnowUpdated 2026-08-20
Download on Hugging Face
Parameters22.3B
Context256K
Layers53
Architectureqwen35
Smallest quant11.1 GB
Quick answer

Qwen3.8 23B Mini Me Bf16 needs about 13.4 GB of memory at BF16 (a 11.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.1 GB.

Qwen3.8 23B Mini Me Bf16 – a vision‑capable, 22.3B‑parameter model

Qwen3.8 23B Mini Me Bf16 is a 22.3B‑parameter model with a 262144‑token context window. It retains vision capabilities and is designed for coding, agentic work, and long multi‑turn conversations. The model is smaller and faster than Qwen3.8‑27B while maintaining similar performance.

Good at

  • Vision tasks
  • Long multi‑turn conversations
  • Coding and tool calling

Limits

  • No standard benchmark metrics
  • Limited to 262144 context tokens
  • Requires BF16 quantization

Best for

  • Local inference on high‑VRAM GPUs
  • Vision‑enabled LLM applications
  • Agentic workflows

Who it’s for. Developers and researchers who need a vision‑capable LLM with a large context window and a smaller footprint than the 27B variant. The model is suitable for local deployment on machines with sufficient VRAM and CPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1611.1 GB 13.4 GB
Too big Get file →

The BF16 quantization file is 11.11 GB and requires approximately 13.4 GB of memory at 8 k context. For lower VRAM budgets, a Q3_K_M quant would reduce size, but it is not available in the provided file list. Use the BF16 file if you have at least 13.4 GB of VRAM.

What GPU do you need for Qwen3.8 23B Mini Me Bf16?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is BF16 (11.1 GB file, about 13.4 GB in use).

Which Qwen3.8 23B Mini Me Bf16 quant should you choose?

BF16 (11.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters22.3B
Layers53
Trained context262,144 tokens
KV cache (fp16)212 KB per token

Source

Quantized bytorchsnow
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,206
Last updated2026-08-20

Frequently asked questions about Qwen3.8 23B Mini Me Bf16

How much VRAM does Qwen3.8 23B Mini Me Bf16 need?

About 13.4 GB at BF16 with an 8K context window. That is the 11.1 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 Qwen3.8 23B Mini Me Bf16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.8 23B Mini Me Bf16 GGUF?

It depends on the quant: BF16 is 11.1 GB.

What context length does Qwen3.8 23B Mini Me Bf16 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.8 GB at 8K and 7.1 GB at 32K.

Where can I download Qwen3.8 23B Mini Me Bf16 GGUF?

The files are on Hugging Face in the torchsnow/Qwen3.8-23B-Mini-Me-bf16-Q3_K_M-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 23B Mini Me Bf16 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?

The BF16 quant requires about 13.4 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does this model support vision?

Yes, it retains vision capabilities from the original architecture.

Is there a smaller quant available?

Only the BF16 quant is provided; no other quantizations are listed.

Other GGUFs of Qwen3.8-23B-Mini-Me-bf16

Similar models

Browse all →

More from torchsnow

All by torchsnow →

More Qwen models

All Qwen →

Other medium models

All medium models →