MiMo V2.6 Flash MOPD

Q3_K_M · spiritfather / Yamz · Measured configuration

79.39 / 100 Mango weighted score · 220.28 min matched workload · 12/12 mechanical agent passes

The selected Q3_K_M GGUF from spiritfather's MiMo V2.6 Flash MOPD Yamz Uncensored release, pinned to the exact package used in Mango.

Benchmark results · Files · Download · Runtime · Provenance · Full collection

Join Infinity on Discord

Get model support, request models and quants, discuss benchmarks, and follow new releases and model improvements.

Join the Infinity community

All model tests, per-question scores, experiment history and scoring methods

Qwen effort study — separate full-404 cohort: medium 82.87/100 versus xhigh 84.41/100; paired difference +1.54 points (95% interval [-1.71, +4.82]). 404 collected questions, 403 valid questions graded per effort; one invalid reference annotation excluded symmetrically. The historical 202-question cross-model comparison below is unchanged. Study, timing and blind subjective results.

Preserved and documented by isilicon / Mango. The original model, modification and quantization remain the upstream creators' work. This repository adds attributed preservation and exact-configuration evaluation, with the selected source bytes unchanged.

At a glance

GB is decimal and GiB is binary. Payload size is disk/storage size, not a claim that the model fits in the same amount of VRAM. Runtime, KV cache, working memory and companions add their own requirements.

Mango evaluation

It passed 18/20 local coding tests and all 12 mechanical agent cases. Its 85.00 cyber domain and 90.00 instruction-following score are stronger than its 65.47 combined social/EQ score.

The workload took 220.28 minutes, about 9.19 times Qwen27's. Two genuine native length finishes remain part of the results. Time sums successful saved requests across the host wipe and excludes downtime.

Domain scores equally average their component task means. The overall score applies the weights above. EQ is continuous; the 12-case mechanical agent pass rate is only one component of the agentic domain.

Task-level quality and uncertainty

These are small released subsets and local graders. HumanEval/BFCL scores are not the complete official benchmark pipelines. Agent checks cover completion, evidence, permissions and applicable pricing totals; other answer semantics remain unjudged.

Recorded performance

Workload time excludes loading, restarts, wipe downtime and idle gaps. Latency/TTFT summaries cover suite requests only. The reported token rate divides engine usage counts by request time; it is not native decode throughput and token accounting differs across engines. No concurrent-serving result is implied.

Matched cohort comparison

The old mixed GLM row is a historical, internally capped baseline whose exact weights are unavailable. Other rows also differ in quant, engine, context and effort. Point ranks do not settle the quality ordering.

Paired score differences

Intervals use 10,000 paired task-stratified bootstrap resamples, seed 41, with fixed task/domain weights. An interval containing zero does not establish a quality winner. See methodology for scope and definitions.

Download the current full numerical report and methodology. The original compact evaluation is retained as the earlier preservation snapshot; its model score is unchanged, while the current report includes the expanded cohort. The numerical report contains aggregate statistics and hashes; no prompts or generated answers are published.

Runtime and compatibility

Mango used llama.cpp with automatic GPU fitting/offload, host RAM and Q8 KV caches. The 151.61GB selected package exceeds the test GPU's VRAM capacity; its disk size is not a VRAM requirement estimate.

32,768-token configured benchmark context; saved responses report native engine-default effort.

The local evaluation covers text/tool tasks. It does not establish the full advertised context ceiling, image/audio quality or every optional speculative-decoding path. Publisher capabilities and Mango-verified behavior are separate scopes.

Companion artifacts

No separate companion mirror is declared in this selected manifest. This does not imply that every optional upstream projector, draft head or multimodal path is included; consult the exact file list.

Files and integrity

Full paths, byte sizes and complete SHA-256/Git blob identities are in SOURCE_MANIFEST.json. Available original README/license/notice files are also preserved. MIRROR_STATUS.json records the earlier source-file verification; MODEL_CARD_STATUS.json records this documentation refresh separately.

Download and use

The commands pin the already-verified mirror weight revision. Documentation can advance on main without changing that preserved weight snapshot. Keep original subfolders and all shards.

python -m pip install -U huggingface_hub

hf download isilicon/mango-mimo26-flash-mopd-uncensored-q3km \
  MiMo-V2.6-Flash-MOPD-Yamz-Uncensored.Q3_K_M.gguf \
  --revision e842719b9d6ad87fdda51699c920095e9771ef0c \
  --local-dir ./weights/mimo26-flash-mopd-uncensored-q3km

Load example and setup scope

llama-server \
  --model ./weights/mimo26-flash-mopd-uncensored-q3km/MiMo-V2.6-Flash-MOPD-Yamz-Uncensored.Q3_K_M.gguf \
  --host 127.0.0.1 --port 8080 --ctx-size 32768 \
  --jinja --flash-attn on --cache-type-k q8_0 --cache-type-v q8_0

This is a minimal text-serving example for a compatible build, not a replay of every benchmark fitting/offload flag. The recorded configuration and engine caveats define the tested scope.

Provenance and license

The source credits the XiaomiMiMo base and the Yamz modification lineage. The publisher's own benchmarks, context claims and quantization descriptions are retained in the upstream reference; Mango's measurements below cover only this Q3_K_M setup.

Original notices, base-model conditions and the publisher's stated limitations still apply. Downloadable preservation does not add new license rights. Source-described refusal modification and publisher-side benchmark claims have not been independently re-measured by this Mango task cohort.

Original publisher documentation

The unchanged upstream README and pinned source card retain the original usage guidance, technical discussion, attribution, caveats and citations.

Read the complete original publisher card

Source reference. The following is the original publisher's documentation. Its other quants, full-model files, context claims and benchmark tables can exceed the selection in this mirror. Relative asset/file URLs are qualified to the pinned original source; publisher measurements remain separate from Mango measurements.

MiMo-V2.6-Flash-MOPD-Yamz-Uncensored — GGUF

🧬 Ablation: yamz-labs/MiMo-V2.6-Flash-MOPD-EXL3-Yamz-Uncensored · base: XiaomiMiMo/MiMo-V2.6-Flash-MOPD
📦 Source GGUF: QuantaPlanta/MiMo-V2.6-Flash-MOPD-MXFP4-GGUF
🛠️ Runs on llama.cpp (master)
📊 Benchmarked on CaliperBench
💬 Discord

[!Note] All credit for the uncensoring goes to yamz-labs, who fitted the refusal direction and per-layer strengths for MiMo-V2.6-Flash-MOPD and published them as uncensor_direction.st + uncensor_spec.json. Credit for the base model goes to XiaomiMiMo (309B total / ~15B active MoE, 256 experts, 8 active), and for the lossless GGUF conversion these quants start from to QuantaPlanta. These are quantizations only.

[!Important] Why this repo exists. yamz-labs' uncensor is applied at runtime by their Kyojin engine on an EXL3 pack (tested on AMD Strix Halo); stock ExLlamaV3, TabbyAPI, llama.cpp, LM Studio and Ollama ignore it and serve the base model with its refusals. This repo bakes the same edit into the weights so it works in any llama.cpp-based runtime — Apple Silicon, CUDA, CPU — with no special engine or flag.

[!Tip] Benchmarked on CaliperBench — a creative-writing benchmark scoring prose craft, roleplay and willingness rather than general intelligence.

Refusals

100 held-out harmful prompts (harmful_behaviors eval split), thinking on, greedy, 1024-token cap, classified by CaliperBench's refusal detector. Same prompts and settings for every row.

The edit is one global direction: it lowers refusals and over-refusals together. It is not a safety evaluation and says nothing about what the model will or will not produce.

Provided quants

KLD, PPL and same-top-token are measured against the stock model (QuantaPlanta's MXFP4 GGUF, which is lossless against the release) on wiki.test.raw, 100 chunks at ctx 512, llama-perplexity --kl-divergence. So each number is the combined cost of the uncensor edit and the quantization, which is what you actually pay versus running stock. The table fills in as each size lands.

Loading (any current llama.cpp)

llama-server -m MiMo-V2.6-Flash-MOPD-Yamz-Uncensored.Q4_K_M.gguf -ngl 99 -fa on -c 32768 -ctk q8_0 -ctv q8_0 --jinja

Thinking: on by default in MiMo's template. For non-thinking replies pass chat_template_kwargs: {"enable_thinking": false} per request.

Sampling: yamz-labs and Xiaomi recommend temperature 1.0, top-p 0.95; greedy decoding is not recommended for generation.

How it was made

1. Source. QuantaPlanta/MiMo-V2.6-Flash-MOPD-MXFP4-GGUF: a stock convert_hf_to_gguf.py of the release — bf16 attention/dense, routed experts in MXFP4. MiMo ships its experts natively in MXFP4, so this file is lossless against the original weights.

2. Bake the edit. yamz-labs' spec states the equivalent weight form of their runtime edit, W ← W − w(L)·r̂ r̂ᵀ W, applied to the writers into the residual stream: attn_output (layers 11–47) and the MLP/MoE output (ffn_down in dense layer 0, routed ffn_down_exps in layers 1–46), with their per-layer strengths. MTP layers, router, gate/up experts, norms and embeddings are untouched. Math is float32; the edited tensors are written as BF16 into a master GGUF (~320 GB), and every edited tensor was checked against the expected |1 − w| shrink of the direction component (e.g. layer 20 experts 0.222× vs 0.221× expected).

   • The edited experts are deliberately not re-encoded to MXFP4: that erased ~80% of the expert edit, and that build refused 74/100.

3. Quantize each size from that master with llama-quantize: routed experts take the nominal type; every non-expert tensor (attention, dense and MTP FFN, nextn.eh_proj, token embeddings, output head) is pinned to Q8_0; router, norms and attention sinks stay F32. Static quants, no imatrix. --allow-requantize is needed only because the unedited gate/up experts are MXFP4 in the master — the model's native precision, so this is still a first quantization.

   llama-quantize --allow-requantize \
     --tensor-type attn_qkv=q8_0 --tensor-type attn_output=q8_0 \
     --tensor-type 'ffn_(gate|up|down)\.weight=q8_0' --tensor-type nextn.eh_proj=q8_0 \
     --token-embedding-type q8_0 --output-tensor-type q8_0 \
     MASTER.gguf MiMo-V2.6-Flash-MOPD-Yamz-Uncensored.Q4_K_M.gguf Q4_K_M
   

Built with llama.cpp master 4e416ee (stock mimo2 support, no patches).

Use

The edit lowers refusals. You decide how to use the model and you answer for it under the laws that apply to you. Intended uses: research, evaluation, red-teaming, creative writing and private deployment. Do not use it to produce illegal content or to target people, or in a public service without your own filtering and moderation.

License

MIT, inherited from XiaomiMiMo/MiMo-V2.6-Flash-MOPD.

Preservation record

Selected source bytes are verified against pinned metadata; the original eight graded mirrors also passed the previously recorded anonymous 1 MiB weight-prefix checks. This is not a full independent-device restore/load test. Hugging Face repository copies share a provider and do not guarantee permanent storage.

Collection · Source manifest · Original documentation