The LLMCheck index estimates MiMo-V2.6-Distill-Qwen-9B at ~79 tok/s on an M5 Max at Q4_K_M, a figure from its published bandwidth model, not a measured run. It needs about 8 GB of unified memory. It is Xiaomi's 9.41B dense model, released under the MIT licence.
Want to run MiMo-V2.6-Distill-Qwen-9B faster — or step up to bigger models? Find your Mac →This is an LLMCheck index estimate from its published two-term bandwidth model, not a measured run; the index labels it so everywhere it appears. Own this Mac? Submit a real run →
| Metric | Value |
|---|---|
| Tokens per second | estimated~79 tok/s |
| Provenance | estimate · how estimates are made |
| Quantization | Q4_K_M |
| Engine | llama.cpp |
| Figure dated | 2026-10 |
| Minimum RAM | 8 GB |
| Parameters | 9.41B |
| Chip bandwidth | 614 GB/s |
Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (8 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.
| Speed | Quant | Engine | Mac RAM | Context | Source | Note |
|---|---|---|---|---|---|---|
| estimated79 tok/s | Q4_K_M | llama.cpp | 64 GB | — | LLMCheck estimator | — |
Ollama — the index has not verified an Ollama tag for MiMo-V2.6-Distill-Qwen-9B, so it doesn’t print one (a guessed tag fails with “pull model manifest: file does not exist”). Search the Ollama library →
MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:
Downloads: Hugging Face repo → · model card →
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
| Chip | Speed | Quant | Engine | Bandwidth |
|---|---|---|---|---|
| M4 Pro | estimated38 tok/s | Q4_K_M | llama.cpp | 273 GB/s |
| M6 | estimated24 tok/s | Q4_K_M | llama.cpp | 170 GB/s |
| M4 | estimated17 tok/s | Q4_K_M | llama.cpp | 120 GB/s |
| M1 | estimated10 tok/s | Q4_K_M | llama.cpp | 68 GB/s |
Xiaomi's MIT-licensed 9B distillation of MiMo-V2.6 onto Qwen3.5-9B (21 Sep 2026), released as a research SFT checkpoint for agentic RL rather than a polished chat model; vendor-reported SWE-bench Pro 44.6 on Xiaomi's scaffold. 5.8 GB at Q4_K_M, so it runs on an 8–16 GB Mac; use the ggml-org GGUF or a patched chat template.
MIT licence · 9.41B · 262K context · LLMCheck capability 21/50 · see its leaderboard rank →
MiMo-V2.6-Distill-Qwen-9B needs about 8 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.
See how MiMo-V2.6-Distill-Qwen-9B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard