LocalFit
Submit a benchmark

MiMo-V2.6-Flash-MOPD

XiaomiMiMo/MiMo-V2.6-Flash-MOPD

Released2026-09-27Size309B MoE · 15B activeRoleAssistantLicensemitContext1M config max

Where it runs 8K context · ≥ 5 t/s floor

SetupBest planMemoryGenerate
8 GB GPU + 32 GB RAMDoes not fit
12 GB GPU + 32 GB RAMDoes not fit
16 GB GPU + 64 GB RAMDoes not fit
24 GB GPU + 64 GB RAMDoes not fit
32 GB GPU + 128 GB RAMDoes not fit
2× 24 GB GPUs + 128 GB RAMDoes not fit
96 GB workstation GPU + 256 GB RAMnative fp8vLLMGPU streams weights from RAM · 67 GiB in RAMKV unknown≤ 8.9 t/s Ceiling
Mac, 24 GBDoes not fit
Mac, 48 GBDoes not fit
Mac, 128 GBDoes not fit
Mac, 512 GBDoes not fit
DGX Spark 128 GBDoes not fit
Ryzen AI Max+ 395, 128 GBDoes not fit
CPU only, 64 GB DDR5-5600 dual channelDoes not fit

Same plan engine as the planner, with its default reserves and RAM. How plans are chosen.

Files exact Hugging Face bytes

ArtifactSizeFilesRevisionSource
Native safetensors mixed/custom native; quant_method=fp8, store_dtype=mxfp4; st
XiaomiMiMo/MiMo-V2.6-Flash-MOPD
161 GiB129b12f557335HF files

Not found in the representative quant search (not proven unavailable): GGUF FP16, GGUF Q8_0, GGUF Q5_K_M, GGUF Q4_K_M, MLX 8-bit, MLX 4-bit, EXL3, AWQ, GPTQ. Complete selected file sets; projectors, MTP/draft and lookup files are listed separately and budgeted only by plans that use them. File bytes are not allocated memory.

Quality

AA evaluated modeIndexLiveCodeBenchTerminal-Bench 2.1GPQAHLESource
MiMo-V2.6-Flash37.974.3%——35.1%source

Arena text rating

1,455

CI 1449–1462 · 10,917 votes · published 2026-10-15 · dataset

Hosted MiMo-V2.6 Flash family comparator only: exact evaluated RL/MOPD checkpoint and local quant are unknown; never inherit this as verified local checkpoint quality.

Publisher-reported benchmarks

None extracted from the model card.

AA and Arena describe the hosted model in the stated mode, not each quantized file; scores are never inherited by base, pruned, abliterated or quantized variants and never averaged together.

How to run it

No model-specific recipe in the research. The planner binds the backend’s documented command template (llama.cpp, Ollama, LM Studio, MLX, vLLM) to your plan: open a plan’s details.

Recipes are source examples (settings are the publisher’s or author’s, not measured optima) and were not executed by LocalFit. A downloadable file does not prove your backend build supports the architecture.

Reported speeds 0

No reported measurement yet. Submit one.