---

license: apache-2.0

base_model: Qwen/Qwen3.6-35B-A3B

tags:

- qwen

- qwen3.6

- 35b

- a3b

- moe

- mtp

- nextn

- speculative-decoding

- gguf

- quantized

- imatrix

pipeline_tag: text-generation

---

Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn (GGUF)

35B MoE Qwen3.6-A3B trunk (3B active) + embedded NextN-MTP head, quantized for single-GPU inference.

• Trunk: IQ4_XS (imatrix-calibrated)
• MTP head: Q8_0 (NextN, kv_only_nextn=true)
• File size: ~18.3 GB
• Min VRAM: ~21 GB at 32K ctx with KV Q8/Q8

The MTP head is embedded inside the GGUF — no separate drafter file. Recent llama.cpp builds activate it via --spec-type draft-mtp.

Quick start (no spec decode)

llama-server -m Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn.gguf \
  -ngl 999 -fa on -c 32768 --parallel 1 \
  -ctk q8_0 -ctv q8_0 --kv-unified \
  --host 0.0.0.0 --port 8080 --jinja

With speculative decoding (recommended)

Requires llama.cpp built from master after ggml-org/llama.cpp#22673:

llama-server -m Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn.gguf \
  -ngl 999 -fa on -c 32768 --parallel 1 \
  -ctk q8_0 -ctv q8_0 --kv-unified \
  --spec-type draft-mtp \
  --spec-draft-n-max 2 \
  --spec-draft-p-min 0.0 \
  --host 0.0.0.0 --port 8080 --jinja

For A3B MoE, smaller --spec-draft-n-max wins — accept rate decays faster with depth than dense models. n_max=2 is the sweet spot. For MoE at deeper chains (n>=3), --spec-draft-p-min 0.0 outperforms p_min=0.75 because per-step sampler overhead from top_k+softmax exceeds the accept-rate savings on this arch.

Benchmarks

Single-stream decode on a 24 GB consumer GPU (RTX 3090 Ti), CUDA build, full-GPU offload, FA on, N=512 generated tokens, 5-warm-run mean.

Production config (ctx=32K, KV Q8/Q8)

| config | decode tok/s |

|---|---|

| no spec (greedy) | ~120 (varies) |

| --spec-type draft-mtp --spec-draft-n-max 2 --spec-draft-p-min 0.0 | ~200 (+67%) |

Smaller ctx variant (ctx=8192, KV q4_0/q4_0, p_min=0)

| n_max | tok/s |

|---|---|

| 1 | 189.5 |

| 2 | 198.7 (+24%) |

| 3 | 191.2 |

| 4 | 167.6 |

n_max=2 wins; deeper chains regress (MoE accept rate falls faster with depth).

Quant details

• Trunk weights: IQ4_XS calibrated with an imatrix derived from a mixed-domain calibration set.
• MTP head: kept at Q8_0 (NextN). Sensitive to precision.
• KV cache: Q8_0/Q8_0 recommended.

llama.cpp requirements

• Build supporting Qwen3.6 NextN MTP (LLM_ARCH_QWEN35MOE_MTP). Merged upstream in #22673.
• --spec-draft-p-min 0.75 requires recent llama.cpp that honors p_min on the DRAFT_MTP path.

Sister models

• Without imatrix: localweights/Qwen3.6-35B-A3B-MTP-IQ4_XS-Q8nextn-GGUF
• 27B dense variant: localweights/Qwen3.6-27B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF

Reference

• Base model: <https://huggingface.co/Qwen/Qwen3.6-35B-A3B>
• MTP architecture: NextN-style embedded prediction layer, kv_only_nextn=true.

Apache 2.0 license.