18 6 27

ManniX PRO

ManniX-ITA

https://github.com/mann1x

mann1x

AI & ML interests

None yet

Recent Activity

updated a model about 10 hours ago

ManniX-ITA/Qwen3.6-27B-Omnimerge-v4

updated a model about 10 hours ago

ManniX-ITA/Qwen3.6-27B-Omnimerge-v4-GGUF

posted an update about 17 hours ago

🚀 Gemma-4-A4B 98e v5-coder — code-leaning 20.8B MoE (4B-active), C6 layer-relevance-weighted prune of Gemma 4 26B-A4B. Best 20B-class coder I've shipped. 📊 SCORES (NVFP4A16, vLLM 0.20.2, greedy, EVAL_PROTOCOL v3) HumanEval 98.17 — HumanEval+ 92.68 — LCB-medium-55 v4 85.45 MATH-500 92.00 — GPQA-D 68.69 — IFEval 94.00 vs v4: +1.22 HE / +1.22 HE+ / +7.27 LCB-medium Top of the 14–22B coder band: +8.6pp HE over Qwen2.5-Coder-14B-Instruct (89.6 → 98.17). HE+ sanity-audited — no memorization, no silent-empty. 📦 EXTENSIVE GGUF SWEEP (16 plain + IQ tiers + 5 CD recipes, all imatrix-calibrated) Q8_0 — 21.16 GB — 93.90% (cohort top) Q4_K_S — 12.21 GB — 93.29% ⭐ plain sweet spot IQ4_XS — 11.01 GB — 93.29% ⭐ sub-12 GB top ⭐ TWO EXCELLENT SUB-10 GB CONTRIBDYNAMIC CD PICKS (per-layer + IQ-codebook overrides) CD-IQ4_K_M (Canary W) — 10.29 GB — 92.07% — recommended sub-11 GB CD-IQ3_XS_L — 9.27 GB — 90.24% — smallest viable code-grade ⚔️ SAME-RIG vs Qwen2.5-Coder-14B-Instruct (RTX 3090, greedy HE+) 11 GB band: v5-coder IQ4_XS wins +9.75pp at -1.49 bpw 12 GB band: Q4_K_S wins +8.53pp 8 GB band: IQ2_S wins +0.61pp at lower bpw bf16: https://huggingface.co/ManniX-ITA/gemma-4-A4B-98e-v5-coder-it GGUF: https://huggingface.co/ManniX-ITA/gemma-4-A4B-98e-v5-coder-it-GGUF NVFP4A16: https://huggingface.co/ManniX-ITA/gemma-4-A4B-98e-v5-coder-NVFP4A16 Ollama: https://ollama.com/mannix/gemma4-98e-v5-coder ——— 🆕 BONUS — Qwen3.6-27B-Omnimerge-v4-MTP-GGUF Same v4 weights with the native MTP head retained for llama.cpp speculative decoding (PR #22673, --spec-type draft-mtp). 7 imatrix tiers Q8_0 → IQ2_M. HumanEval: 2.0x decode tok/s MBPP: 2.33x decode tok/s Both at +1-2pp pass@1 vs the non-MTP build. GPQA Diamond comparison in flight. MTP-GGUF: https://huggingface.co/ManniX-ITA/Qwen3.6-27B-Omnimerge-v4-MTP-GGUF

View all activity

Organizations

None yet

Posts 6

Post

🚀 Gemma-4-A4B 98e v5-coder — code-leaning 20.8B MoE (4B-active), C6 layer-relevance-weighted prune of Gemma 4 26B-A4B. Best 20B-class coder I've shipped.

📊 SCORES (NVFP4A16, vLLM 0.20.2, greedy, EVAL_PROTOCOL v3)

HumanEval 98.17 — HumanEval+ 92.68 — LCB-medium-55 v4 85.45
MATH-500 92.00 — GPQA-D 68.69 — IFEval 94.00
vs v4: +1.22 HE / +1.22 HE+ / +7.27 LCB-medium

Top of the 14–22B coder band: +8.6pp HE over Qwen2.5-Coder-14B-Instruct (89.6 → 98.17). HE+ sanity-audited — no memorization, no silent-empty.

📦 EXTENSIVE GGUF SWEEP (16 plain + IQ tiers + 5 CD recipes, all imatrix-calibrated)

Q8_0 — 21.16 GB — 93.90% (cohort top)
Q4_K_S — 12.21 GB — 93.29% ⭐ plain sweet spot
IQ4_XS — 11.01 GB — 93.29% ⭐ sub-12 GB top

⭐ TWO EXCELLENT SUB-10 GB CONTRIBDYNAMIC CD PICKS (per-layer + IQ-codebook overrides)

CD-IQ4_K_M (Canary W) — 10.29 GB — 92.07% — recommended sub-11 GB
CD-IQ3_XS_L — 9.27 GB — 90.24% — smallest viable code-grade

⚔️ SAME-RIG vs Qwen2.5-Coder-14B-Instruct (RTX 3090, greedy HE+)

11 GB band: v5-coder IQ4_XS wins +9.75pp at -1.49 bpw
12 GB band: Q4_K_S wins +8.53pp
8 GB band: IQ2_S wins +0.61pp at lower bpw

bf16:
ManniX-ITA/gemma-4-A4B-98e-v5-coder-it

GGUF:
ManniX-ITA/gemma-4-A4B-98e-v5-coder-it-GGUF

NVFP4A16:
ManniX-ITA/gemma-4-A4B-98e-v5-coder-NVFP4A16

Ollama:
https://ollama.com/mannix/gemma4-98e-v5-coder

———

🆕 BONUS — Qwen3.6-27B-Omnimerge-v4-MTP-GGUF

Same v4 weights with the native MTP head retained for llama.cpp speculative decoding (PR #22673, --spec-type draft-mtp). 7 imatrix tiers Q8_0 → IQ2_M.

HumanEval: 2.0x decode tok/s
MBPP: 2.33x decode tok/s
Both at +1-2pp pass@1 vs the non-MTP build. GPQA Diamond comparison in flight.

MTP-GGUF:
ManniX-ITA/Qwen3.6-27B-Omnimerge-v4-MTP-GGUF

Post

242

v1.1.0 was Claude + Ollama chat. Eight releases later the stack is a grounded research pipeline plus a local-first memory layer; the token crunch is operational now, not a quality wall.

🚀 claude-hooks v1.8.3 — highlights since v1.1.0.

🧠 /consultants v2 — agentic council, matured.
🛠 tool_executor — PLAN→REPORT lane runs read_file / grep / glob over the codebase before the researcher speaks; claims grounded in tool output, not vibes.
✍️─ coder — sandboxed write_file role with per-language model routing (50KB/file, 1MB/lane caps).
🛡️ CitationLinter — three-layer verifier at the researcher boundary; every path:line claim checked against an mtime-cached code_graph. Catches fabricated filenames before they launder through critics + synthesizer.

💾 M14 cross-session memory (default on).
LangGraph BaseStore wired across four namespaces: research / tool_results / project / user. Per-namespace TTL: research=30d, tool_results=24h, project+user=forever. Hourly Caliber-style distillation reaper summarizes
expiring research into the durable project namespace BEFORE deletion — episodic → semantic, like human consolidation. Originals only dropped after a successful summary write.

🔁 sqlite_vec — full pgvector parity (v1.7).
Hybrid recall via RRF over vector cosine + BM25 (FTS5). KG surface: kg_create_entities / kg_add_observations / kg_create_relations / kg_search_nodes. Bundled sqlite-vec-mcp launcher went 3→8 tools so Cursor / Codex /
OpenWebUI / Claude Desktop share the same .db. Lazy schema migration carries v1.6.x dbs in place, non-destructive.

🧩 llamafile chat + embed (v1.4 + v1.5).
HyDE / reflect / consolidate / get-advice / consultants route to a daemon-supervised local llamafile via the llamafile:// model prefix. Multi-instance LRU, per-label idle reap, sticky CPU fallback. Stack runs
offline now.

🐧 Linux / macOS / Windows. PostgreSQL OR SQLite. Local OR cloud LLMs.

🔗 github.com/mann1x/claude-hooks

View all Posts

Collections 1

models 45

datasets 1

ManniX-ITA/osync-code

Viewer • Updated Jan 12 • 1 • 16