Step-3.7-Flash-180B-LynnStyle-GLM52-SFT-GPT55-RL

Step-3.7-Flash-180B-LynnStyle-GLM52-SFT-GPT55-RL

This main repository hosts the final RL2 BF16 weights and mirrors the accepted GGUF release under GGUF/. The dedicated GGUF-only repository is nerkyor/Step-3.7-Flash-180B-LynnStyle-GLM52-SFT-GPT55-RL-GGUF.

BF16 files live at the repository root. GGUF tiers in this repository use the same accepted layout as the GGUF-only repository: GGUF/Q8/, GGUF/Q5/, GGUF/Q4/, and GGUF/Q3/. Q2 is not published.

Llama.cpp MUST READ BEFORE LAUNCH

Official llama.cpp prebuilt binaries without this compatibility patch will fail to load this GGUF.

Reason: unpatched official llama.cpp builds cannot recognize the pruned Step35 / Step 3.7 MoE layout where the routed expert count differs by layer. They still read step35.expert_count as a single u32, while this pruned MoE stores expert counts as a per-layer array.

For example, llama-b9892-bin-win-vulkan-x64 fails during hyperparameter loading with:

key step35.expert_count has wrong type arr but expected type u32

This is not a corrupted-shard issue and is not caused by the MTP sidecar. Use a patched Step 3.7 / LynnStyle-compatible build, or apply the patch and rebuild.

If you are not comfortable rebuilding llama.cpp, give the Patch and Usage notes links below to Codex or another coding agent, and ask it to apply the patch to your target llama.cpp source tree and rebuild.

Reference runtime: llama.cpp 8c146a8366304c871efc26057cc90370ccf58dad; the release tests used CUDA llama-server built from the patched llama.cpp tree.

For newer official source trees or binaries such as b9892, apply the same patch logic and rebuild; re-downloading GGUF shards will not fix this error.

Important GGUF parser note: Hugging Face / ModelScope GGUF auto-detection may parse a standalone MTP sidecar or one shard and show misleading metadata such as 3B params, 5-bit, or 2.49GB. That is not the main model. This repository uses multi-shard mixed-precision LynnStyle GGUF. Download the complete GGUF/Q4/, GGUF/Q5/, GGUF/Q8/, or GGUF/Q3/ shard set plus the matching MTP sidecar, and follow the README launch template. The platform hardware-compatibility panel is not authoritative for this mixed-precision release.

Naming note: GLM5.2-SFT / GPT5.5-RL describes post-training data provenance, not weight provenance. Most SFT Agent/ReAct trajectories were generated, rewritten, or cleaned with GLM 5.2 API assistance; most RL preference pairs and judge signals came from a GPT-5.5/Codex-style review policy. No GLM or GPT weights are mixed into this model.

Repository Scope

This is the GGUF repository for Step-3.7-Flash-180B-LynnStyle-GLM5.2-SFT-GPT5.5-RL.

The 180B label comes from the pruned effective MoE scale: after expert-workload analysis and task-scope protection, about 8%, roughly 1000 low-contribution experts, were removed from the original MoE.

LynnStyle is the full local-inference method chain: localization-guided protection of key layers, experts, and tensor families; dynamic layered pruning of low-contribution paths; targeted SFT/RL to reduce overthinking, empty answers, non-delivery, and parse failures; and calibrated mixed-precision quantization that keeps core layers, hot experts, router paths, attention, lm_head, and MTP protected.

This repository is for GGUF quantized files, runtime smoke results, MTP single/concurrent checks, and quantized gate metrics. BF16 weights belong in the main repository.

Text Scope and MTP Sidecars

This release currently claims text reasoning, code, and Agent/ReAct text capability. It does not claim image input. The original dyn263 BF16 source retained multimodal traces such as vision_config and vision_encoder.py, but this final RL2 merge, export, quantization, and evaluation path did not validate the complete vision stack: vision-tower weights, projector / mmproj, image processor, image-token alignment, and llama.cpp image-input smoke tests.

MTP sidecars are optional speculative-decoding draft files. They accelerate inference together with a main GGUF model; they are not vision files and cannot be used as standalone main models.

• LynnStyle Q8 uses GGUF/Q8/Step-3.7-Flash-MTP-Q8_0.gguf.
• LynnStyle Q5 uses GGUF/Q5/Step-3.7-Flash-MTP-Q8_0.gguf.
• LynnStyle Q4 uses GGUF/Q4/Step-3.7-Flash-MTP-Q5_K_M.gguf.

LynnStyle GGUF Strategy

Q8 is the quality baseline. The most important endpoint tier in this release is LynnStyle Q4: around 90GB, aimed at fitting a 180B-class MoE into a 96GB/R6000 single-card setup.

The previous way to fit this model class into R6000 was closer to a quality-collapsed Q3. LynnStyle Q4 is tested early because it decides whether the 96GB endpoint route is real.

LynnStyle Q4 Profile

LynnStyle Q4 Profile F6 is not a uniform IQ4_XS file. It is explicit core protection plus interleaved imatrix calibration plus lower precision for cold MoE experts. The dry-run target is 93216.74 MiB / 91.03 GiB, leaving a more realistic margin for a 96GB/R6000 setup.

The protection table is combined with a 2026-07-06 interleaved imatrix calibration set that rotates through LBC, Coding100, ReAct, GPQA, MMLU, native SFT, and RL-preference prompts. It does not use benchmark answer keys as supervised training labels.

These figures are the evidence behind the pruning and quantization policy: MMLU/GPQA and LBC/Coding100 do not activate exactly the same experts; L39-L44 are high-risk in both scopes; code tasks expose specialized experts that reasoning-only traces do not fully cover. LynnStyle is therefore not blind pruning and not uniform low-bit quantization.

Available Tiers

Download guidance:

• LynnStyle Q4: download every shard under GGUF/Q4/, from 00001-of-00005 to 00005-of-00005.
• LynnStyle Q5: download every shard under GGUF/Q5/, from 00001-of-00005 to 00005-of-00005.
• LynnStyle Q8: download every Q8 shard under GGUF/Q8/.
• MTP sidecar: for Q8, download GGUF/Q8/Step-3.7-Flash-MTP-Q8_0.gguf; for LynnStyle Q5, download GGUF/Q5/Step-3.7-Flash-MTP-Q8_0.gguf; for LynnStyle Q4, download GGUF/Q4/Step-3.7-Flash-MTP-Q5_K_M.gguf.

Metrics

Final RL2 Q8+MTP:

LynnStyle Q4 imatrix Profile F6:

LynnStyle Q5 imatrix:

RL2 is the final release because it preserves the main public gates while reducing heavy-thinking and non-delivery failure modes. An RL1 comparison run was stopped at 81/117 = 69.23% on GPQA, making RL2 the stronger release for this objective.

MTP Recommendation

LynnStyle Q4 has completed the C1/C2/C4 by draft N=1..4 MTP matrix on the 2026-07-06 R6000 setup. TPS is llama.cpp predicted_tokens_seconds.

For 96GB/R6000 LynnStyle Q4, use GGUF/Q4/Step-3.7-Flash-MTP-Q5_K_M.gguf as the draft model. LynnStyle Q5 and Q8 use the Step-3.7-Flash-MTP-Q8_0.gguf sidecar in their own tier directories. The Q8_0 MTP sidecar is about 3.71GB and is not the default Q4 pairing.

LynnStyle Q5 MTP:

File-size fit notes:

• LynnStyle Q4: about 93.16 GiB including its Q5_K_M MTP sidecar; recommended for 96GB/R6000 with conservative context first.
• LynnStyle Q5: about 123.23 GiB including its Q8_0 MTP sidecar; recommended for 128GB-class memory.
• LynnStyle Q8: about 182.55 GiB including its Q8_0 MTP sidecar; use multi-GPU / 190GB+ class memory.

llama.cpp Templates

LynnStyle Q8 + MTP

MAIN_GGUF="GGUF/Q8/Step-3.7-Flash-180B-LynnStyle-GLM52-SFT-GPT55-RL-Q8_0-00001-of-00005.gguf"
MTP_GGUF="GGUF/Q8/Step-3.7-Flash-MTP-Q8_0.gguf"

./llama-server \
  -m "$MAIN_GGUF" \
  -ngl 999 \
  --split-mode layer \
  --ctx-size 32768 \
  --parallel 1 \
  --cont-batching \
  --jinja \
  --reasoning on \
  --reasoning-format deepseek \
  --spec-type draft-mtp \
  --model-draft "$MTP_GGUF" \
  --spec-draft-ngl 999 \
  --spec-draft-n-max 2 \
  --spec-draft-p-min 0.6 \
  --host 0.0.0.0 \
  --port 8000

LynnStyle Q5 imatrix + MTP

MAIN_GGUF="GGUF/Q5/Step-3.7-Flash-180B-LynnStyle-GLM52-SFT-GPT55-RL-Q5-imatrix-MTP-00001-of-00005.gguf"
MTP_GGUF="GGUF/Q5/Step-3.7-Flash-MTP-Q8_0.gguf"

./llama-server \
  -m "$MAIN_GGUF" \
  -ngl 999 \
  --split-mode layer \
  --ctx-size 8192 \
  --parallel 1 \
  --cont-batching \
  --jinja \
  --reasoning on \
  --reasoning-format deepseek \
  --spec-type draft-mtp \
  --model-draft "$MTP_GGUF" \
  --spec-draft-ngl 999 \
  --spec-draft-n-max 3 \
  --spec-draft-p-min 0.6 \
  --host 0.0.0.0 \
  --port 8000

LynnStyle Q5 imatrix + MTP

MAIN_GGUF="GGUF/Q5/Step-3.7-Flash-180B-LynnStyle-GLM52-SFT-GPT55-RL-Q5-imatrix-MTP-00001-of-00005.gguf"
MTP_GGUF="GGUF/Q5/Step-3.7-Flash-MTP-Q8_0.gguf"

./llama-server \
  -m "$MAIN_GGUF" \
  -ngl 999 \
  --split-mode layer \
  --ctx-size 8192 \
  --parallel 1 \
  --cont-batching \
  --jinja \
  --reasoning on \
  --reasoning-format deepseek \
  --spec-type draft-mtp \
  --model-draft "$MTP_GGUF" \
  --spec-draft-ngl 999 \
  --spec-draft-n-max 3 \
  --spec-draft-p-min 0.6 \
  --host 0.0.0.0 \
  --port 8000

LynnStyle Q4 imatrix + MTP

MAIN_GGUF="GGUF/Q4/Step-3.7-Flash-180B-LynnStyle-GLM52-SFT-GPT55-RL-Q4-imatrix-MTP-00001-of-00005.gguf"
MTP_GGUF="GGUF/Q4/Step-3.7-Flash-MTP-Q5_K_M.gguf"

./llama-server \
  -m "$MAIN_GGUF" \
  -ngl 999 \
  --ctx-size 8192 \
  --parallel 1 \
  --cont-batching \
  --jinja \
  --reasoning on \
  --reasoning-format deepseek \
  --spec-type draft-mtp \
  --model-draft "$MTP_GGUF" \
  --spec-draft-ngl 999 \
  --spec-draft-n-max 3 \
  --spec-draft-p-min 0.6 \
  --host 0.0.0.0 \
  --port 8000

---