MiniMax-M2 — Expert-Pruned (keep-192/256), GGUF
A research artifact on structurally compressing a 230B Mixture-of-Experts coding agent (MiniMax-M2: 256 experts/layer, top-8) by pruning experts — keeping it a working agent in a real tool-using loop, not just a fluent generator. This is the keep-192 point: 192 of 256 experts kept (top-K by measured code/agentic activation), ~30% smaller, still solves real SWE tasks.
👉 Full field report:
ARTICLE.md.
The headline: capability scales smoothly with the expert budget
Evaluated as a real coding agent (a harness driving the model through a Dockerized repo: read, edit, run tests) on a 6-instance SWE-bench Verified probe set (the exact instances the un-pruned model resolves 6/6), served via Ollama:
| Variant | Size (GGUF) | Experts kept | SWE resolved |
|---|
| Full M2 (IQ2_M) | 78 GB | 256 / 256 | 6 / 6 |
| keep-192 (this repo) | ~55 GB | 192 / 256 | 3 / 6 |
| keep-160 | 46 GB | 160 / 256 | 1 / 6 |
| IQ1 (all experts, 1.8-bit) | 48 GB | 256 / 256 | 0 / 6 |
Two findings worth taking away:
- No cliff — agentic capability degrades smoothly as you remove experts (6 → 3 → 1), it doesn't collapse. You can drop a quarter of the experts and keep half the solving.
- At a fixed size, prune > uniform-extreme-quant — keep-160 (46 GB, 160 experts at ~2.7-bit) resolves where IQ1 (48 GB, all 256 at 1.8-bit) resolves nothing. Concentrating the bit budget on fewer experts beats spreading it thin.
These models are untrained (pure pruned quant, no fine-tune) — so the resolves are genuine compressed-M2 capability, not memorization.
Use it
1# Ollama (the GGUF is in this repo):
2ollama create m2-pruned192 -f Modelfile
3ollama run m2-pruned192
Or point any llama.cpp/GGUF runtime at M2-pruned192-IQ2.gguf. Use a generous context for agent loops (the M2 chat template + stop tokens are baked into the Modelfile).
Reproduce
1# Prune the kept experts out of an IQ2_M GGUF of MiniMax-M2 (clean slice, no re-quant):
2python prune_gguf_experts.py \
3 --in MiniMax-M2-IQ2_M.gguf --out M2-pruned192.gguf \
4 --keep 192 --strategy file --keep-file keep192_experts.json
keep192_experts.json is the per-layer expert keep-set (top-K by measured activation on a code/agentic calibration corpus).
Limitations
- Research artifact, not a production release. At ~55 GB it solves 3/6 of this probe set; the full 78 GB quant solves 6/6 — pruning trades size for capability along the curve above.
- Untrained. A recovery fine-tune ("heal") on top should push it further up the curve (separate work).
- Honest framing: this is not "better than the full model" — it's a smaller point on a clean size↔capability curve, and at a fixed budget it beats a same-size uniform low-bit quant.
License
Apache-2.0, inheriting MiniMax-M2's terms. This repo adds a pruning recipe + a pruned GGUF derived from a quantized MiniMax-M2.
