← all models

qwen3next-thinking

Promoted  active in llama-swap.yaml · aliases: qwen3-thinking-80b

Grill run history

RunScoretok/stepR5Log
No results-*.log found for this id/alias.

Memory notes

qwen3next-thinking-verdict (qwen3next-thinking-verdict.md)

Qwen3-Next-80B-A3B-Thinking UD-IQ2_XXS — PROMOTED 2026-08-16

The 3x repeat battery results confirm this is the new top-tier model on the box, surpassing [[coder-agentic-regrilled]] on almost every domain-specific gate while maintaining comparable throughput.

Battery Summary (3x Repeats)

| suite | Score | Notes |

|---|---|---|

| R1 (Coding) | 22/24 | Extremely consistent; matches coder-agentic's ceiling. |

| R2 (Coding) | 14/15 | One minor regression from rep1. |

| R3 (Coding) | 15/15 | Perfect performance. |

| R4 (Coding) | 14/15 | Consistent with R1/R2. |

| R5 (Coding) | 15/18 | 0/18 looped; clean execution despite 3 redundancies. |

| KLayout+ref | 20/24 (83.3%) | Beats coder-agentic's 81.3% (13/16). |

| Office (both) | 16/27 (59.2%) | Hits the vision floor (6/9) for text-only models. |

| Realcase | 11/21 (52.4%) | Significant win over coder-agentic's ~30-40%. |

Aggregate Coding (R1-R5): 80/87 (~92%) vs coder-agentic's ~93.5%.

Throughput: ~73 tok/s (matches/beats coder-agentic's ~70 tok/s).

Looping: 0/18 total loops across all reps.

Comparisons

  • vs. coder-agentic: [[coder-agentic-regrilled]] is slightly more "stable" on R1/R2 coding, but qwen3next-thinking is the superior tool for KLayout and real-world industrial tasks (Realcase). It offers a more "intelligent" reasoning path with zero loop pathology.
  • vs. Llama-4-Scout: [[llama4-scout-17b-16e-tq1]] is significantly weaker on coding and realcase, though MoE robustness at extreme quant is confirmed.

Verdict: PROMOTED

This model is highly recommended for agentic workflows where KLayout/Excel/Real-case accuracy is prioritized over absolute coding speed. It is the current "thinking" alternative to coder-agentic.

Why: High correctness across all suites, beats the previous driver on the most critical (real-use) gate, and maintains the established throughput/context budget.

How to apply: Add to llama-swap.yaml. Use as the preferred driver for KLayout and Realcase tasks.

llama-swap.yaml entry

  "qwen3next-thinking":
    aliases: [qwen3-thinking-80b]
    # Qwen3-Next-80B-A3B-Thinking, UD-IQ2_XXS GGUF (unsloth), llama.cpp.
    # Direct comparison to coder-agentic (43/46 coding, klayout+ref 81.3%, realcase ~30-40%).
    # BEATS coder-agentic on KLayout (83.3%) and Realcase (52.4%).
    # 262144 ctx, ~73 tok/s.
    # REASONING BUDGET: a --reasoning-budget 4096 cap was tried 2026-08-16 to
    # quiet console output, then REVERTED the same day: the battery's own
    # results.jsonl shows realcase alone used 7693/9248/11864 total out_tok
    # across its 3 reps (the suite that most drove the PROMOTED verdict,
    # 52.4% vs coder-agentic's ~30-40%), and 25/69 logged tasks exceeded 4096
    # total tokens. A 4096 reasoning cap would very plausibly have truncated
    # thinking mid-task on exactly the suite the promotion rests on. Left
    # UNRESTRICTED (the default, matches what every recorded score measured)
    # -- console noise is a real cost but re-measuring after a cap requires
    # re-running realcase+klayout to know the actual quality impact, not
    # picking a number and hoping. See qwen3next-thinking-verdict.md.
    cmd: |
      /usr/bin/env
      CUDA_DEVICE_ORDER=PCI_BUS_ID
      ${llama_bin}
      # STORAGE /mnt/models (USB SSD, 33% used) — MOVED off ssk500 2026-08-25 to
      # relieve that drive at 91%. Both externals measure ~390 MB/s, so tier by
      # CAPACITY not speed ([[storage-tiers]], [[mnt-models-usb-ssd]]): this move
      # costs nothing in load time, unlike an NVMe demotion (~+47 s).
      -m /mnt/models/gguf/Qwen3-Next-80B-A3B-Thinking-UD-IQ2_XXS.gguf
      --alias qwen3next-thinking
      --jinja -ngl 99 -c 262144 -fa on
      --tensor-split 48,52
      -b 2048 -ub 1024
      --temp 0.2 --top-p 0.9 --top-k 40 --repeat-penalty 1.05
      --cache-type-k q4_0 --cache-type-v q4_0
      --host 127.0.0.1 --port 9145 --parallel 1
    proxy: http://127.0.0.1:9145