Opus Candid 8B V3 needs about 8.4 GB of memory at Q6_K (a 6.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 6.7 GB (Q6_K) to 8.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Opus Candid 8B V3 – a 8.19B‑parameter Qwen3 model fine‑tuned for candid, bilingual dialogue
Opus Candid 8B V3 is a 8.19B‑parameter Qwen3 model fine‑tuned on 1,558 Zipf‑weighted conversations. It supports reasoning and tool use, and is bilingual in English and Spanish. The model is released under the Apache‑2.0 license.
Good at
- Reasoning and instruction following
- Tool integration
- Bilingual English/Spanish dialogue
Limits
- No vision support
- Context limited to 40960 tokens
- Requires 8.4–10.4 GB VRAM for 8K context
Best for
- Short conversational agents
- Agent tasks with tool calls
- Bilingual customer support
Who it’s for. Developers building lightweight, conversational agents that need candid, opinionated responses in English or Spanish. The model is suitable for local deployment with moderate VRAM and no vision requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 6.7 GB | 8.4 GB | Too big | Get file → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → |
For 8 GB VRAM use the Q6_K quantized file (6.72 GB, ~8.4 GB memory at 8K context). For 10 GB VRAM use Q8_0 (8.71 GB, ~10.4 GB memory at 8K context). Estimates are approximate.
What GPU do you need for Opus Candid 8B V3?
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 Q8_0 (8.7 GB file, about 10.4 GB in use).
Which Opus Candid 8B V3 quant should you choose?
Q6_K (6.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Opus Candid 8B V3
How much VRAM does Opus Candid 8B V3 need?
About 8.4 GB at Q6_K with an 8K context window. That is the 6.7 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 Opus Candid 8B V3 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Opus Candid 8B V3 GGUF?
It depends on the quant: Q6_K is 6.7 GB, Q8_0 is 8.7 GB.
What context length does Opus Candid 8B V3 support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Opus Candid 8B V3 GGUF?
The files are on Hugging Face in the Verdugie/Opus-Candid-8B-V3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Opus Candid 8B V3 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 Opus Candid 8B V3 on 8 GB VRAM?
Yes, the Q6_K quantized file requires about 8.4 GB VRAM at 8K context, which fits within an 8 GB GPU with some overhead.
Does this model support vision tasks?
No, Opus Candid 8B V3 is a language‑only model and does not include vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.