Qwen3.8 20B Minitron needs about 13.9 GB of memory at Q4_K_M (a 11.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 11 quants, from 7.8 GB (Q2_K) to 20.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.9 GB.
Qwen3.8 20B Minitron – a pruned, 19.3B‑parameter Qwen model
Qwen3.8 20B Minitron is a structurally‑pruned derivative of Qwen3.8‑27B, reduced from 64 to 44 decoder layers. It retains the Qwen architecture and supports reasoning, tools, and vision. The model is released under the apache‑2.0 license.
Good at
- reasoning
- tools
- vision
Limits
- trained context 262144 tokens
- no official benchmark scores
- experimental release
Best for
- short‑form reasoning tasks
- tool‑integrated workflows
- vision‑enabled prompts
Who it’s for. Developers and researchers needing a lightweight Qwen variant with reasoning and vision capabilities. The model is suitable for experimentation and integration into custom LLM pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 7.8 GB | 9.8 GB | Too big | Get file → | |
| Q3_K_S | 8.8 GB | 10.8 GB | Too big | Get file → | |
| Q3_K_M | 9.6 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_L | 10.4 GB | 12.3 GB | Too big | Get file → | |
| IQ4_XS | 11.0 GB | 13.0 GB | Too big | Get file → | |
| Q4_K_S | 11.3 GB | 13.2 GB | Too big | Get file → | |
| Q4_K_M | 11.9 GB | 13.9 GB | Too big | Get file → | |
| Q5_K_S | 13.4 GB | 15.4 GB | Too big | Get file → | |
| Q5_K_M | 13.8 GB | 15.8 GB | Too big | Get file → | |
| Q6_K | 15.8 GB | 17.8 GB | Too big | Get file → | |
| Q8_0 | 20.5 GB | 22.5 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (7.82 GB file, 9.8 GB memory). For 12 GB VRAM use Q4_K_S (11.27 GB file, 13.2 GB memory). For 16 GB VRAM use Q5_K_M (13.82 GB file, 15.8 GB memory). Estimates are approximate.
What GPU do you need for Qwen3.8 20B Minitron?
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: the best quant that fits is Q3_K_M (9.6 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (13.8 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (20.5 GB file, about 22.5 GB in use).
Which Qwen3.8 20B Minitron quant should you choose?
Q4_K_M is the usual starting point for Qwen3.8 20B Minitron: it balances file size and quality well. Here it is a 11.9 GB file.
The Q8_0 file is 20.5 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.
If memory is tight, the smallest file is Q2_K at 7.8 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
Source
Frequently asked questions about Qwen3.8 20B Minitron
How much VRAM does Qwen3.8 20B Minitron need?
About 13.9 GB at Q4_K_M with an 8K context window. That is the 11.9 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 20B Minitron on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.8 20B Minitron GGUF?
It depends on the quant: Q2_K is 7.8 GB, Q3_K_S is 8.8 GB, Q3_K_M is 9.6 GB, Q3_K_L is 10.4 GB, IQ4_XS is 11.0 GB, Q4_K_S is 11.3 GB and 5 more.
What context length does Qwen3.8 20B Minitron support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.5 GB at 8K and 5.9 GB at 32K.
Where can I download Qwen3.8 20B Minitron GGUF?
The files are on Hugging Face in the mradermacher/Qwen3.8-20B-Minitron-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 20B Minitron 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 20B Minitron on 8 GB VRAM?
Use the Q2_K quant; it requires about 9.8 GB of VRAM at 8 k context.
Does this model support vision tasks?
Yes, the model has detected vision ability, but no specific vision benchmarks are provided.
What license applies to this model?
The model is released under the apache‑2.0 license.