Guanaco vs Llama vs Vicuna vs OpenChat
A side-by-side look at scores, pricing and features — with RECATOOLS' ASEAN-aware verdict for each.
Guanaco
The 2023 research chatbots that demonstrated QLoRA 4-bit fine-tuning
Visit
|
Llama
Meta's downloadable LLM family, last updated with Llama 4 in April 202...
Visit
|
Vicuna
LMSYS's 2023 LLaMA fine-tune that led to FastChat and Chatbot Arena
Visit
|
OpenChat
Open 7B and 8B models trained with C-RLFT, dormant since May 2024
Visit
|
|
|---|---|---|---|---|
| RECATOOLS Score | 4 / 10 | 8.3 / 10 | 4 / 10 | 6.3 / 10 |
| Capability | ||||
| Value for money | ||||
| Ease of use | ||||
| ASEAN readiness | ||||
| API quality | ||||
| Pricing | Open Source | Open Source | Open Source | Open Source |
| Free tier | Free download of code (MIT) and adapter weights (Apache 2.0), subject to the LLaMA licence for the base model | Free weight downloads (Llama 2, 3.x and 4) under Meta's Llama community licences, after accepting the licence | Free weight downloads on Hugging Face; v1.5 under the Llama 2 Community License, earlier versions non-commercial | Free weights and code: OpenChat 3.5 under Apache 2.0, OpenChat 3.6 under the Llama 3 licence |
| Paid from | — | — | — | — |
| Has API | ✗ | ✓ | ✗ | ✗ |
| Open source | ✓ | ✓ | ✓ | ✓ |
| Free to use | ✓ | ✓ | ✓ | ✓ |
| Users | 100k+ downloads | 10m+ downloads | 1m+ downloads | 200k+ downloads |
| Founded | 2023 | 2023 | 2023 | 2023 |
| Maker | University of Washington | Meta Platforms | LMSYS Org | Tsinghua University |
| Verdict | Guanaco is worth knowing for the method, not the model. QLoRA showed that 4-bit quantisation plus LoRA adapters could fine-tune a 65B model on one 48GB GPU, and that machinery now lives in bitsandbytes and Hugging Face P... |
Llama 2 and 3 made Meta's family the default starting point for self-hosted and fine-tuned models, and the weights from Llama 2 through Llama 4 remain free to download from Hugging Face and Kaggle. Llama 4 Scout and Mave... |
Vicuna showed in March 2023 that a LLaMA fine-tune on shared ChatGPT conversations could make a capable chatbot for about $300 of training, and the project gave the field FastChat and Chatbot Arena, now run by the compan... |
OpenChat earned attention for C-RLFT, a clean way to learn from mixed-quality instruction data, and for 7B models the project measured as competitive with early-2023 ChatGPT. The weights are still free to download and ru... |
| Full review → | Full review → | Full review → | Full review → |
Comparisons cover up to 4 tools. Scores are RECATOOLS editorial assessments; verify current pricing on each vendor's site.