WhizReviewer ML Pro 123B needs about 76.7 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 0.0 GB to 86.5 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.
WhizReviewer ML Pro 123B – a 123‑billion‑parameter text‑only LLM for expert paper review
WhizReviewer ML Pro 123B is a 123‑billion‑parameter generative model based on Mistral‑Large‑2. It is trained on paper‑review comments in machine learning, CV, NLP, and MM. The model is purely text and does not support vision.
Good at
- Generating expert‑level review comments
- Simulating multiple reviewers and a meta‑reviewer
- Rapid paper iteration
Limits
- No vision support
- License prohibits formal review use
- Large VRAM requirement
Best for
- Academic paper drafting
- Research feedback loops
- Auto‑research pipelines
Who it’s for. Researchers and academic teams needing automated, high‑quality review feedback. The model is suitable for internal use where formal review work is not required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.5 GB | Fits | Get file → | |
| IQ1_S | 26.0 GB | 29.4 GB | Too big | Get file → | |
| IQ1_M | 28.4 GB | 31.8 GB | Too big | Get file → | |
| IQ2_XXS | 32.4 GB | 35.9 GB | Too big | Get file → | |
| IQ2_XS | 36.1 GB | 39.5 GB | Too big | Get file → | |
| IQ2_S | 38.4 GB | 41.8 GB | Too big | Get file → | |
| Q2_K_S | 41.6 GB | 45.1 GB | Too big | Get file → | |
| IQ2_M | 41.6 GB | 45.1 GB | Too big | Get file → | |
| Q2_K | 45.2 GB | 48.6 GB | Too big | Get file → | |
| IQ3_XXS | 47.0 GB | 50.5 GB | Too big | Get file → | |
| IQ3_XS | 50.1 GB | 53.6 GB | Too big | Get file → | |
| Q3_K_S | 52.8 GB | 56.3 GB | Too big | Get file → | |
| IQ3_S | 53.0 GB | 56.4 GB | Too big | Get file → | |
| IQ3_M | 55.3 GB | 58.7 GB | Too big | Get file → | |
| Q3_K_M | 59.1 GB | 62.6 GB | Too big | Get file → | |
| Q3_K_L | 64.6 GB | 68.0 GB | Too big | Get file → | |
| IQ4_XS | 65.4 GB | 68.9 GB | Too big | Get file → | |
| Q4_0 | 69.3 GB | 72.8 GB | Too big | Get file → | |
| Q4_K_S | 69.6 GB | 73.0 GB | Too big | Get file → | |
| Q4_K_M | 73.2 GB | 76.7 GB | Too big | Get file → | |
| Q4_1 | 76.7 GB | 80.2 GB | Too big | Get file → | |
| Q5_K_S | 84.4 GB | 87.8 GB | Too big | Get file → | |
| Q5_K_M | 86.5 GB | 89.9 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (25.96 GB file, 29.4 GB memory at 8 k context). For 16‑GB VRAM, IQ2_XS (36.08 GB file, 39.5 GB memory). For 24‑GB VRAM, Q4_K_M (73.22 GB file, 76.7 GB memory). Estimates are approximate.
What GPU do you need for WhizReviewer ML Pro 123B?
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: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 32 GB VRAM: the best quant that fits is IQ1_M (28.4 GB file, about 31.8 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (41.6 GB file, about 45.1 GB in use).
Which WhizReviewer ML Pro 123B quant should you choose?
Q4_K_M is the usual starting point for WhizReviewer ML Pro 123B: it balances file size and quality well. Here it is a 73.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about WhizReviewer ML Pro 123B
How much VRAM does WhizReviewer ML Pro 123B need?
About 76.7 GB at Q4_K_M with an 8K context window. That is the 73.2 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 WhizReviewer ML Pro 123B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of WhizReviewer ML Pro 123B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 26.0 GB, IQ1_M is 28.4 GB, IQ2_XXS is 32.4 GB, IQ2_XS is 36.1 GB, IQ2_S is 38.4 GB and 17 more.
What context length does WhizReviewer ML Pro 123B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.
Where can I download WhizReviewer ML Pro 123B GGUF?
The files are on Hugging Face in the mradermacher/WhizReviewer-ML-Pro-123B-i1-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 WhizReviewer ML Pro 123B use?
Hugging Face lists the license as other. 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 WhizReviewer ML Pro 123B on 8 GB VRAM?
No, the smallest quant requires 25.96 GB file and 29.4 GB memory at 8 k context. 8 GB VRAM is insufficient.
Does the model support image input?
No, the model is purely text and does not support vision.
Is the model licensed for formal peer review?
No, the license prohibits use for formal review work.