CARDS Qwen3.6 27B API needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.9 GB (Q2_K) to 29.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
CARDS Qwen3.6 27B API – fine‑tuned for climate‑contrarian claim classification
CARDS Qwen3.6 27B API is a 27.3 billion‑parameter model fine‑tuned on the CARDS taxonomy for climate‑contrarian claim classification. It supports reasoning, tools, and vision, and can be run with standard inference engines such as vLLM or llama.cpp.
Good at
- Climate‑contrarian claim classification
- Multimodal image + text inputs
- Reasoning and tool use
Limits
- Requires 8 k context for memory estimates
- No explicit vision model size limits listed
- Apache‑2.0 license
Best for
- Classifying climate claims in research
- Building multimodal classification pipelines
- Evaluating claim veracity in policy analysis
Who it’s for. Researchers and developers needing a specialized climate‑claim classifier. The model is ready for direct loading with transformers, vLLM, or llama.cpp, and includes a LoRA adapter for further fine‑tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.9 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_S | 12.3 GB | 14.9 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_L | 14.6 GB | 17.2 GB | Too big | Get file → | |
| IQ4_XS | 15.4 GB | 18.1 GB | Too big | Get file → | |
| Q4_K_S | 15.8 GB | 18.5 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| Q5_K_S | 19.0 GB | 21.7 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 → |
For 8 k context, the Q4_K_M quant (~16.81 GB file) uses ~19.5 GB RAM, suitable for 24 GB VRAM setups. If VRAM is limited to 8 GB, consider Q2_K (~10.86 GB file) which uses ~13.5 GB RAM. For higher fidelity, Q5_K_M (~19.54 GB file) uses ~22.2 GB RAM.
What GPU do you need for CARDS Qwen3.6 27B API?
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 Q3_K_S (12.3 GB file, about 14.9 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).
Which CARDS Qwen3.6 27B API quant should you choose?
Q4_K_M is the usual starting point for CARDS Qwen3.6 27B API: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 29.0 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 10.9 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 CARDS Qwen3.6 27B API
How much VRAM does CARDS Qwen3.6 27B API need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 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 CARDS Qwen3.6 27B API on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of CARDS Qwen3.6 27B API GGUF?
It depends on the quant: Q2_K is 10.9 GB, Q3_K_S is 12.3 GB, Q3_K_M is 13.5 GB, Q3_K_L is 14.6 GB, IQ4_XS is 15.4 GB, Q4_K_S is 15.8 GB and 5 more.
What context length does CARDS Qwen3.6 27B API 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 CARDS Qwen3.6 27B API GGUF?
The files are on Hugging Face in the mradermacher/CARDS-Qwen3.6-27B-API-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 CARDS Qwen3.6 27B API 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 smallest quant Q2_K uses ~13.5 GB RAM at 8 k context, which exceeds 8 GB VRAM. A lower‑precision quant is required for 8 GB VRAM.
Does the model support image inputs?
Yes, the base Qwen3.6 family supports image inputs via the OpenAI‑compatible image_url content part, and this fine‑tune preserves that capability.
What license applies to this model?
The model is released under the Apache‑2.0 license.