google/diffusiongemma-26B-A4B-it (released 2026-06-10) — Google's first
open-weight text-diffusion LLM. Does NOT run in Ollama (unknown arch
'diffusion-gemma'); built llama-diffusion-cli from ggml-org/llama.cpp PR
#24423 and smoke-tested Q4_K_M on steel141's 3090 Ti.
- New reference doc with specs, build recipe, throughput, and gotchas
- CORPUS_ollama_variants.md: "not an Ollama variant" callout
- README index line for the reference doc
- scripts/diffusiongemma-smoketest/ harness + raw result logs
Findings: ~106 tok/s effective / ~2030 tok/s in-step-parallel; correct code
+ coherent reasoning; <|channel>thought CoT eats the 256-tok canvas so strict
short formats need block budgeting. nvidia-smi index != CUDA index on steel141
(select 3090 Ti by UUID). Experimental research artifact, not homelab-deployable
until diffusion arch merges to llama.cpp mainline.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- 11.9B dense, 256K ctx, Q4_K_M, vision+audio+tools+thinking
- requires Ollama >= 0.30.5; upgraded steel141 0.20.4 -> 0.30.8 to pull
- smoke-tested 2026-06-16: text/vision/tools pass at 70 tok/s 100% GPU on 3090 Ti
- flag: mort-bakeoff 0.20.4 thinking-in-context pin now needs re-verification
- audio capability listed by ollama show but UNVERIFIED through API
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Patches the top-level corpus docs with the 13 findings flagged during the
2026-04-18 canonical tooling research pass. tooling/README.md now marks each
finding [merged: <file>] or [flagged] for provenance.
- CORPUS_ollama_variants.md: annotate gemma4:26b as MoE (25.2B total / 3.8B
active, 8-of-128 experts + 1 shared). Note Q4_K_M inference is standard
(the "MoE quality degrades at 4-bit" caveat is training-only). Add note
that audio on E-series is NOT available via Ollama — llama.cpp mmproj
or vLLM only.
- CORPUS_capabilities.md: native system role, configurable thinking mode,
first trained tool use (vs Gemma 1/2/3 proof-of-concept), native object
detection with bbox output in 1000x1000 coords, pointer to EmbeddingGemma
for retrieval (Gemma 4 has no embedding mode).
- CORPUS_tool_calling_format.md: add Chat Template Context section
documenting the <|turn>/<turn|> asymmetric brackets (new in Gemma 4,
replaced <start_of_turn>/<end_of_turn>) plus <|think>, <|channel>,
<|image>, <|audio> tokens. Add HF transformers Alternative section
showing processor.parse_response with response_schema.
- GOTCHAS.md: add MEDIUM gotcha for abandoned google/gemma_pytorch (no
Gemma 4 support since 2025-05-30). Expand fine-tuning section with FA2/FA4
head_dim=512 break, fused LoRA kernel issues, 26B A4B training-quant
guidance, new tool-call tokens as learned embeddings.
- SYNTHESIS.md: add banner pointing to tooling/ for canonical upstream
material. Add embeddinggemma row to Model Selection table.
Also:
- Add .gitignore excluding .backup/ (local scratch per global CLAUDE.md
convention, not needed in tracked history) and __pycache__/.
- Add .claude/handoffs/2026-04-18-canonical-tooling-research.md so future
sessions can pick up cold — facts verified, open threads, what changed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Architecture specs, benchmarks, gotchas, Ollama settings, tool calling
format, and implementation patterns from Simon and AI_Visualizer.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Mortdecai