ThinkingCap Qwen3.6 27B MTP needs about 18.4 GB of memory at Q4_K_M (a 15.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 3.2 GB (Q8_0) to 54.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
ThinkingCap Qwen3.6 27B MTP – a versatile, low‑bit GGUF model
ThinkingCap Qwen3.6 27B MTP is a 0.461 billion‑parameter Qwen family model with 262144‑token context. It supports reasoning and vision and is distributed under the apache‑2.0 license. The model is available in multiple quantizations, including a full‑lossless bf16 master.
Good at
- Reasoning tasks
- Vision integration
- Speculative decoding with MTP
Limits
- No vision support on non‑Blackwell GPUs
- Large VRAM needed for higher‑bit quantizations
- License requires compliance with apache‑2.0
Best for
- Chatbots needing fast inference
- Image‑captioning pipelines
- Research prototyping
Who it’s for. Developers and researchers who need a compact, multi‑token‑prediction capable LLM that can run on a range of GPUs, from RTX 50‑series to workstations. The model is suitable for both production and experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 3.2 GB | 5.8 GB | Fits | Get file → | |
| IQ3_M | 12.8 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_M | 15.7 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| — | 18.2 GB | 20.9 GB | Too big | Get file → | |
| Q5_K_M | 19.5 GB | 22.2 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → | |
| Q8_0 | 29.0 GB | 31.7 GB | Too big | Get file → | |
| BF16 | 54.7 GB | 57.3 GB | Too big | Get file → |
For a 24 GB VRAM card, use the Q4_K_M‑MTP quant (file size 15.72 GB, estimated 18.4 GB memory at 8 k context). If you have 12 GB VRAM, the IQ3_M‑MTP quant (file size 12.77 GB, estimated 15.4 GB memory) fits. For maximum fidelity, the bf16‑MTP quant (file size 54.66 GB, estimated 57.3 GB memory) requires a workstation with >57 GB VRAM.
What GPU do you need for ThinkingCap Qwen3.6 27B MTP?
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: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (12.8 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 22.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).
Which ThinkingCap Qwen3.6 27B MTP quant should you choose?
Q4_K_M is the usual starting point for ThinkingCap Qwen3.6 27B MTP: it balances file size and quality well. Here it is a 15.7 GB file.
The Q8_0 file is 3.2 GB, about 0.2 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 Q8_0 at 3.2 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
Source
Frequently asked questions about ThinkingCap Qwen3.6 27B MTP
How much VRAM does ThinkingCap Qwen3.6 27B MTP need?
About 18.4 GB at Q4_K_M with an 8K context window. That is the 15.7 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 ThinkingCap Qwen3.6 27B MTP on an 8 GB GPU?
Yes, with Q8_0: the 3.2 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ThinkingCap Qwen3.6 27B MTP GGUF?
It depends on the quant: Q8_0 is 3.2 GB, IQ3_M is 12.8 GB, Q3_K_M is 13.5 GB, Q4_K_M is 15.7 GB, Q4_K_M is 16.8 GB, file is 18.2 GB and 4 more.
What context length does ThinkingCap Qwen3.6 27B MTP support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download ThinkingCap Qwen3.6 27B MTP GGUF?
The files are on Hugging Face in the protoLabsAI/ThinkingCap-Qwen3.6-27B-MTP-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 ThinkingCap Qwen3.6 27B MTP 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 the Q4_K_M quant on an RTX 3070 with 8 GB VRAM?
No. The Q4_K_M quant requires at least 18.4 GB memory at 8 k context, which exceeds 8 GB VRAM.
Does the model support vision on all GPUs?
Vision support is available only on GPUs that support NVFP4 tensor cores, such as RTX 50‑series and RTX PRO 6000.
What is the difference between the Q8_0 and Q8_0‑MTP files?
Both contain the same weights; the Q8_0‑MTP file includes the Multi‑Token‑Prediction draft head for speculative decoding.