---
license: apache-2.0
base_model: Qwen/Qwen3-Coder-Next
base_model_relation: quantized
pipeline_tag: text-generation
tags:
- janas
- jns
- local-inference
- cpu-inference
- mixture-of-experts
---

# Qwen3-Coder-Next for Janas-LLM

**On a laptop running Debian 13 Linux, with an Intel Core Ultra 9 185H, its integrated Arc GPU and 32 GB of memory, Janas-LLM reads a prompt at 66 tok/s and writes at 22 tok/s: llama.cpp, on the same laptop, 14 and 2.2.**

| On the same laptop | Janas-LLM | llama.cpp |
|---|---:|---:|
| reading a prompt of 1,024 tokens | 66 tok/s | 14 tok/s |
| writing (16 tokens) | 22 tok/s | 2.2 tok/s |

Measured on 9-11 October 2026: `llama-bench -p 1024 -n 16` and `janas-bench --prompt 1024 --gen 16`, both at their best configuration. On other machines the figures will differ. Details: [Janas README](https://github.com/prabanta-dev/janas#readme).

## The machine these figures come from

- **Debian 13 (trixie) Linux**, x86-64, kernel 6.12.107
- Intel Core Ultra 9 185H: 6 performance cores, 8 efficiency cores, 2 low-power cores; AVX2, FMA, F16C, AVX-VNNI
- its integrated Intel Arc GPU, through the Vulkan driver of Mesa 26.1.6
- 32 GB of DDR5-5600 memory
- a 1 TB NVMe SSD, about 5.7 GB/s reading
- llama.cpp build `2b18470` (18 September 2026), Vulkan backend

The model (48.4 GB) is larger than the laptop's memory: Janas-LLM streams from the NVMe SSD the experts each token needs and keeps the ones that keep coming back in memory. llama.cpp was measured as on Qwen3-Next-80B, with a build without weight repacking: reading with the GPU and the experts left in the file (`-ncmoe 48 --no-host 1 -lm mmap`), writing on the CPU alone, the faster of its ways for each.

These are the model's weights converted to **JNS**, the format of Janas-LLM, the inference engine in C of [Janas](https://github.com/prabanta-dev/janas), for ordinary computers, with or without a GPU. The files are read by Janas-LLM only.

## Get it

Janas-LLM for Linux x86-64 (Ubuntu 22.04, Debian 12 and later), then the model:

```sh
curl -LO https://github.com/prabanta-dev/janas/releases/latest/download/janas-linux-x86_64.tar.gz
tar xf janas-linux-x86_64.tar.gz && cd janas
./janas-get qwen3-coder-next
./janas-chat qwen3-coder-next
```

`janas-get` downloads the files of this repository and checks them against the fingerprints below; `janas-chat` with no model shows the catalog and downloads the one you choose. Building Janas-LLM from its sources instead: [prabanta-dev/janas](https://github.com/prabanta-dev/janas).

## Files

| File | Size | SHA-256 | Converted from |
|---|---:|---|---|
| `qwen3-coder-next-q4km.jns` | 48.41 GB | `0276b0697a05075fec8ab076a757205537804ff41dd7e9dadace7c6993763563` | [Qwen/Qwen3-Coder-Next-GGUF](https://huggingface.co/Qwen/Qwen3-Coder-Next-GGUF) `Qwen3-Coder-Next-Q4_K_M/Qwen3-Coder-Next-Q4_K_M-00001-of-00004.gguf` (catalog name `qwen3-coder-next`: Qwen3-Coder-Next, mixture of experts, for code) |

## What was changed

These files are a modified work of the original model, as the Apache License 2.0 requires to be stated. Nothing was retrained or pruned: each file is a GGUF file quantized by the people named above, rewritten by Janas-LLM's `gguf2jns` in the order Janas reads it, with the metadata carried over. Each (layer, expert) has a slot of its own, so that the experts a token needs can be read from disk on their own. The experts' down matrices were then cut by Janas-LLM's `jns_planes` into three planes of two bits each: a reordering of the same bits, which with all three planes gives back the quantized weights to the last bit.

## Licence and attribution

Licensed under the **Apache License 2.0**, as the original model: see `LICENSE`.

- Model: [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next), by Alibaba Cloud (the Qwen team).
- Quantized GGUF: [Qwen/Qwen3-Coder-Next-GGUF](https://huggingface.co/Qwen/Qwen3-Coder-Next-GGUF), by its authors.
- Converted to JNS by the Janas project with Janas-LLM ([prabanta-dev/janas](https://github.com/prabanta-dev/janas), GPL-3.0-or-later; the licence of the engine does not apply to these files).

The original repository carries no LICENSE file; its card declares Apache 2.0. `LICENSE` here is the licence's text as the Apache Software Foundation publishes it.