---

base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct

license: apache-2.0

library_name: gguf

tags:

- gguf

- llama.cpp

- backpack

---

Qwen3-Coder-30B-A3B-Instruct — Backpack GGUF

GGUF quantizations of Qwen/Qwen3-Coder-30B-A3B-Instruct, tested for llama.cpp-compatible text inference and packaged for Backpack.

Model

| Property | Value |

| --- | --- |

| Original model | Qwen/Qwen3-Coder-30B-A3B-Instruct |

| Original publisher | Qwen |

| Upstream revision | b2cff646eb4bb1d68355c01b18ae02e7cf42d120 |

| Architecture | Qwen3MoeForCausalLM |

| Parameters | 30,532,122,624 |

| 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 | 17.3 GiB | 26.05 GB | Most users |

| Q5_K_M | 20.2 GiB | 30.33 GB | Higher quality |

| Q8_0 | 30.3 GiB | 44.85 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:

llama-completion --model Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf -cnv

Run with Backpack

These artifacts and backpack-model.yaml are prepared for the Backpack AI workspace.

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-30B-A3B-Instruct-Q4_K_M.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: 2026-08-30T21:24:08.172221+00:00
• llama.cpp revision: bdf3955159d7184f44b76091973eeff532890a35
• SHA-256 checksums: see checksums.sha256

• Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf: 5f27bd8085b01b078454eb13e17d0c07cdd2d346f7033713a55d6c2c05c84c43

• Qwen3-Coder-30B-A3B-Instruct-Q5_K_M.gguf: 7249b80c81e43dbbaeb7a68480577b0cf7360b751dd2392ad15039f0a46ee4b9

• Qwen3-Coder-30B-A3B-Instruct-Q8_0.gguf: 8ec8ddf444b5ec40615ab0cb7fda0bf94483b3c5e6de1237991deca430d01b96

Provenance

The source model was resolved to immutable revision b2cff646eb4bb1d68355c01b18ae02e7cf42d120. It was converted with llama.cpp's convert_hf_to_gguf.py and quantized with llama-quantize; the exact tested revision is recorded above and in backpack-model.yaml.

License and attribution

Upstream declares apache-2.0. Review the upstream model card and comply with all applicable terms.

Backpack does not claim ownership of the original model. These artifacts are packaged and quantized distributions of the upstream model.

Disclaimer

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