---
base_model: Qwen/Qwen3-Coder-Next-GGUF
license: apache-2.0
library_name: gguf

tags:
  - gguf
  - llama.cpp
  - backpack

---

# Qwen3-Coder-Next-GGUF — Backpack GGUF

🎒 **Backpack Verified**

GGUF quantizations of [Qwen/Qwen3-Coder-Next-GGUF](https://huggingface.co/Qwen/Qwen3-Coder-Next-GGUF), tested for llama.cpp-compatible text inference and packaged for Backpack. The original publisher produced these GGUF files; Backpack verified and repackaged the immutable artifacts without re-quantizing them.

## Model

| Property | Value |
| --- | --- |
| Original model | `Qwen/Qwen3-Coder-Next-GGUF` |
| Original publisher | Qwen |
| Upstream revision | `b82fb7382639d97b38fa7672e526c760c2fb358e` |
| Architecture | Qwen3NextForCausalLM |
| Parameters | 79,674,391,296 |
| Context length | 262,144 |
| Input modalities | text |
| Output modalities | text |
| License | apache-2.0 |

## Available packages

| Quantization | Size | Approx. RAM | Recommended for |
| --- | ---: | ---: | --- |
| Q4_K_M | 45.1 GiB | 66.35 GB | Most users |
| Q5_K_M | 52.8 GiB | 77.56 GB | Higher quality |
| Q8_0 | 79.0 GiB | 115.5 GB | Plenty of memory |


Memory values are estimates, not guarantees. Runtime configuration and context length change actual use.



## Backpack recommendation

**Recommended: Q4_K_M.** It usually offers a practical quality, size, and speed balance for local inference.

## Run with llama.cpp

Using the llama.cpp revision recorded below:

```bash
llama-completion --model Qwen3-Coder-Next-Q4_K_M/Qwen3-Coder-Next-Q4_K_M-00001-of-00004.gguf -cnv
```

## Run with Backpack

These artifacts and `backpack-model.yaml` are prepared for the [Backpack AI workspace](https://backpack.run).

## Validation

| Package | Integrity | Load | Inference | Tokenizer |
| --- | --- | --- | --- | --- |
| Q4_K_M | passed | passed | passed | passed |
| Q5_K_M | passed | passed | passed | passed |
| Q8_0 | passed | passed | passed | passed |


### Capability qualification: code

Tested with `Qwen3-Coder-Next-Q4_K_M-00001-of-00004.gguf`. These are deterministic smoke tests, not benchmark scores.

| Capability | Status |
| --- | --- |
| chat | passed |
| code_generation | passed |
| structured_tool_arguments | passed |
| tool_calling | passed |
| multi_turn_tool_loop | passed |



- Packaged: 2026-08-31T11:20:27.760656+00:00
- llama.cpp revision: `bdf3955159d7184f44b76091973eeff532890a35`
- SHA-256 checksums: see `checksums.sha256`

- `Qwen3-Coder-Next-Q4_K_M/Qwen3-Coder-Next-Q4_K_M-00001-of-00004.gguf`: `6bcfc9f9c37901eeb92172e2ab871224dab36a453d263bcb2547f737409534da`
- `Qwen3-Coder-Next-Q4_K_M/Qwen3-Coder-Next-Q4_K_M-00002-of-00004.gguf`: `817def0691ee9d08bf3dc4444be7aed29c9e52091e8fa9d97901ce7e7f6f01d3`
- `Qwen3-Coder-Next-Q4_K_M/Qwen3-Coder-Next-Q4_K_M-00003-of-00004.gguf`: `23aa634d47dca9b4ca3ea249384e6f01951b24c83cdc076f37f6f43d6c99883f`
- `Qwen3-Coder-Next-Q4_K_M/Qwen3-Coder-Next-Q4_K_M-00004-of-00004.gguf`: `249c768cc5f130dc731567d6edcbdacc48e14dec9e02c5dbe2b2185d2c5bdb2b`

- `Qwen3-Coder-Next-Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00001-of-00004.gguf`: `d68162877891c4ba309c8601a69721ecfc7be2091ad99e8175a078ae59decdd3`
- `Qwen3-Coder-Next-Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00002-of-00004.gguf`: `3da1a3fda1061009126eb48c7098221653ab63e0a266d3b6d04f5eac3ae9aa74`
- `Qwen3-Coder-Next-Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00003-of-00004.gguf`: `df60c7a55c6e118d4984a829b74df6b9e863dcea749ee7dc25ab5e72913624e1`
- `Qwen3-Coder-Next-Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00004-of-00004.gguf`: `777ac63a6f94272934996b1cfd7e5619c6804e8580ec4e00311d2a465e298c6a`

- `Qwen3-Coder-Next-Q8_0/Qwen3-Coder-Next-Q8_0-00001-of-00004.gguf`: `30b7554fc0c846a5dc3ecf585884c77471f73e3da698a8ba4fabd8e7868c6533`
- `Qwen3-Coder-Next-Q8_0/Qwen3-Coder-Next-Q8_0-00002-of-00004.gguf`: `3f96379de5a5c4655cb378710ea571d5e9cc96f260120a44a6477198efcdc27d`
- `Qwen3-Coder-Next-Q8_0/Qwen3-Coder-Next-Q8_0-00003-of-00004.gguf`: `5dd1ce07eaae95ee430331dc9c6f3120ff88e4211ad3a0cceeaa963f25328504`
- `Qwen3-Coder-Next-Q8_0/Qwen3-Coder-Next-Q8_0-00004-of-00004.gguf`: `76730702c630bf76305139165cb85421858604030851dfd64fe96a5e67cda99d`




## Provenance

The source model was resolved to immutable revision `b82fb7382639d97b38fa7672e526c760c2fb358e`. The GGUF files were quantized by **Qwen** and verified by **Backpack** against the pinned llama.cpp revision recorded above.

## License and attribution

Upstream declares **apache-2.0**. Review the [upstream model card](https://huggingface.co/Qwen/Qwen3-Coder-Next-GGUF) and comply with all applicable terms.



Backpack does not claim ownership of the original model. Backpack did not quantize the upstream GGUF artifacts.

## Disclaimer

Quantization can alter output quality. Memory estimates vary with runtime configuration, context length, and hardware.