---
title: Grawnch/Kimi-K3.1-Pro-Coder
url: https://recentmodel.com/models/Grawnch/Kimi-K3.1-Pro-Coder/
status: archived · low-signal
published: 2026-11-08T01:13:03Z
updated: 2026-11-12T12:31:24Z
source: https://huggingface.co/Grawnch/Kimi-K3.1-Pro-Coder
---

# Grawnch/Kimi-K3.1-Pro-Coder

Grawnch/Kimi-K3.1-Pro-Coder is a full 96-shard (774.97 GB / 721.75 GiB) Strata-Coder 3-Tier Mixed-Bit MoE quantization of moonshotai/Kimi-K3.1-Pro (2.8T parameters, 93 layers, 896 routed experts per MoE layer, topk=16 LatentMoE with SiTU-GLU, KDA linear attention + gated NoPE MLA full attention… Mixture-of-experts, 1270B total (896 experts, 16 per token). Context: 1M tokens (config). License: apache-2.0.


- **Org:** Grawnch
- **Released:** 2026-11-08
- **Status:** archived · low-signal
- **License:** apache-2.0 (permissive)
- **Parameters:** 1270.0B
- **Architecture:** MoE · 896 experts, 16/token · KimiK31ForConditionalGeneration
- **Context:** 1,048,576 tokens (config.json)
- **Task:** image-text-to-text · vision
- **Signal:** 5 HF likes · 658 downloads
- **Archived:** 2026-11-12 (no longer listed by the collector; stats as last seen)

## Runs on

estimate from params; sizing calculation, not tested.

- Q4 ~763.9 GB (estimated): no listed device
- Q8 ~1351.2 GB (estimated): no listed device
- FP16 ~2541.8 GB (estimated): no listed device

## Links

- [Hugging Face](https://huggingface.co/Grawnch/Kimi-K3.1-Pro-Coder)
- [Ollama](https://ollama.com/library/kimi-k3.1-pro)