---
license: mit
library_name: mlx
tags:
- mlx
- code
- repository-exploration
- quantization
base_model: microsoft/FastContext-1.0-4B-SFT
---

# FastContext-1.0-4B-SFT — MXFP4 (MLX)

MXFP4 block-float 4-bit quantization (MLX). Converted from [`microsoft/FastContext-1.0-4B-SFT`](https://huggingface.co/microsoft/FastContext-1.0-4B-SFT) for Apple Silicon / MLX.

FastContext is a repository-exploration **subagent** (Qwen3-4B backbone): given a query it explores a codebase with read-only `Read`/`Glob`/`Grep` tools and returns a `<final_answer>` of `file:line` citations. Designed to feed a larger coding agent (e.g. Mini-SWE-Agent).

- **Disk size**: 2049 MB
- **Decode speed (Apple M5 Pro, cooled)**: 104.2 tok/s (3.1× fp16) · prefill 396.33 tok/s · peak 2.579 GB

## SWE-bench Lite localization

Evaluated on its **native task** — file/line localization — since the model emits citations, not prose. Given a GitHub issue, it explores the repo checked out at `base_commit` and cites the files/lines to change; citations are scored **deterministically** against the gold patch (no LLM judge). Subset: psf/requests, pallets/flask, pylint-dev/pylint, pytest-dev/pytest; 12 instances; max_turns=6; greedy decoding.

| Metric | This variant | fp16 ref |
|---|--:|--:|
| File F1 | 0.4694 | 0.5472 |
| File hit-rate | 0.6667 | 0.6667 |
| All-gold-files-found rate | 0.6667 | 0.6667 |
| Line F1 | 0.0154 | 0.0493 |
| Avg turns | 6.58 | 6.58 |

**Citation agreement vs fp16**: mean file-set Jaccard = **0.45** (1.0 = cites exactly the same files as the fp16 model on the same instances).

## Usage

```bash
# serve (OpenAI-compatible)
python -m mlx_lm.server --model sahilchachra/fastcontext-1.0-4b-sft-mxfp4-mlx --port 8080
# then point the FastContext agent (github.com/microsoft/fastcontext) at
# BASE_URL=http://127.0.0.1:8080/v1
```

## Caveats

- Localization numbers use a fixed query wrapper around each issue (not the official LLM-delegated sub-query), so treat absolute scores as a proxy; the fp16↔mxfp4↔mxfp8 comparison is apples-to-apples.
- Quantized with `mlx-lm` 0.31.3.