---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
base_model: ableforge-ai/ReasonCritic-7B
base_model_relation: finetune
tags:
- chain-of-thought
- critic
- evaluation
- fableforge
- gguf
- imatrix
- llama.cpp
- lm-studio
- ollama
- reasoning
- text-generation
---

# ReasonCritic-7B

> **A reasoning critic — evaluates and improves chain-of-thought.**

[![Downloads](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fmodels%2Ffableforge-ai%2FReasonCritic-7B&query=downloads&label=downloads&color=blue)](https://huggingface.co/fableforge-ai/ReasonCritic-7B) [![Demos](https://img.shields.io/badge/🤗-Live%20Demos-orange)](https://huggingface.co/spaces/fableforge-ai/fableforge-nexus)

Base model: [fableforge-ai/ReasonCritic-7B](https://huggingface.co/fableforge-ai/ReasonCritic-7B)  ·  Part of the **FableForge** ecosystem.

---

## ⚡ Quickest start — Ollama (these pulls credit the source, not a mirror)

```bash
ollama run hf.co/fableforge-ai/ReasonCritic-7B:Q4_K_M
```

## 🦙 llama.cpp

```bash
llama-cli -hf fableforge-ai/ReasonCritic-7B:Q4_K_M -p "Hello!"
```

## 💠 LM Studio
Search **`fableforge-ai/ReasonCritic-7B`** and pick a quant below.

---

## 📦 Provided quants (download one file, not the whole repo)

| File | Quant | Size | Notes |
| ---- | ----- | ---- | ----- |
| [reasoncritic-7b.F16.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.F16.gguf) | `F16` | 14.43 GB | Full precision (unquantized). Reference / conversion. |
| [reasoncritic-7b.Q8_0.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q8_0.gguf) | `Q8_0` | 8.71 GB | Extremely high quality — usually overkill. |
| [reasoncritic-7b.Q6_K.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q6_K.gguf) | `Q6_K` | 6.73 GB | Very high quality, near-perfect. **Recommended** if you have the RAM. |
| [reasoncritic-7b.Q5_K_M.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q5_K_M.gguf) | `Q5_K_M` | 5.85 GB | High quality. **Recommended.** |
| [reasoncritic-7b.Q4_K_M.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q4_K_M.gguf) | `Q4_K_M` | 5.03 GB | ⭐ **Best size/quality balance — default pick for most users.** |
| [reasoncritic-7b.Q4_0.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q4_0.gguf) | `Q4_0` | 4.77 GB | Legacy format — prefer Q4_K_M. |
| [reasoncritic-7b.Q3_K_M.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q3_K_M.gguf) | `Q3_K_M` | 4.12 GB | Lower quality; usable when RAM is tight. |
| [reasoncritic-7b.Q2_K.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q2_K.gguf) | `Q2_K` | 3.28 GB | Very low quality — surprisingly usable. |

**Not sure?** Take **`Q4_K_M`**. Low RAM → **`IQ4_XS`**. Max quality → **`Q6_K`**.

## 🧠 Prompt format (ChatML)

```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```

## 🌌 See it live — the FableForge demos

This family powers a galaxy of free, interactive HF Spaces:

- 🧭 [FableForge Nexus](https://huggingface.co/spaces/fableforge-ai/fableforge-nexus)
- 🍺 [Infinite NPC](https://huggingface.co/spaces/fableforge-ai/infinite-npc)
- 🎭 [Dual-GM](https://huggingface.co/spaces/King3Djbl/dual-gm-simulator)
- 💻 [ShellWhisperer](https://huggingface.co/spaces/King3Djbl/shellwhisperer-terminal)
- 👻 [Ghost Writer](https://huggingface.co/spaces/fableforge-ai/ghost-writer)

---

*⭐ Like & share — it helps people find the source instead of a mirror.*