QW

Candid 3.5

QwenGGUF by VerdugieUpdated 2026-10-26
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant16.9 GB
Quick answer

Candid 3.5 needs about 19.5 GB of memory at Q4_K_M (a 16.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 16.9 GB (Q4_K_M) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Candid 3.5 – a conversational fine‑tuned Qwen 3.5 model

Candid 3.5 is a 26.9 billion‑parameter model fine‑tuned from Qwen3.5‑27B on 3,224 conversations. It is optimized for short, opinionated replies in English and Spanish and requires no system prompt. The model is released under the Apache‑2.0 license.

Good at

  • Short conversational replies
  • Opinionated stance generation
  • English and Spanish dialogue

Limits

  • No vision support
  • Only English and Spanish
  • Requires 8 k context for full performance

Best for

  • Chatbots needing concise opinions
  • Customer support in English/Spanish
  • Rapid prototyping of conversational agents

Who it’s for. Developers building lightweight conversational agents that need quick, opinionated responses in English or Spanish. The model is suitable for applications where system prompts are undesirable and where the Apache‑2.0 license is acceptable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M16.9 GB 19.5 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →
Q8_028.6 GB 31.2 GB
Too big Get file →

For an 8 k context window, the Q4_K_M quantization uses 19.5 GB of VRAM and 16.88 GB of storage. If more VRAM is available, Q6_K uses 24.7 GB and 22.08 GB of storage, while Q8_0 uses 31.2 GB and 28.59 GB of storage. Choose the quant that fits your GPU memory budget.

What GPU do you need for Candid 3.5?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (16.9 GB file, about 19.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which Candid 3.5 quant should you choose?

Q4_K_M is the usual starting point for Candid 3.5: it balances file size and quality well. Here it is a 16.9 GB file.

The Q8_0 file is 28.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byVerdugie
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,956
Last updated2026-10-26

Frequently asked questions about Candid 3.5

How much VRAM does Candid 3.5 need?

About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.9 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 Candid 3.5 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Candid 3.5 GGUF?

It depends on the quant: Q4_K_M is 16.9 GB, Q6_K is 22.1 GB, Q8_0 is 28.6 GB.

What context length does Candid 3.5 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Candid 3.5 GGUF?

The files are on Hugging Face in the Verdugie/Candid-3.5 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Candid 3.5 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 Candid 3.5 on a GPU with 8 GB VRAM?

No. The smallest quant requires 19.5 GB of VRAM at 8 k context, so 8 GB is insufficient.

What languages does Candid 3.5 support?

The model is fine‑tuned for English and Spanish only.

Is the model free to use?

Yes, it is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.5-27B

Similar models

Browse all →

More from Verdugie

All by Verdugie →

More Qwen models

All Qwen →

Other medium models

All medium models →