The LLMCheck index estimates Mistral Medium 3.5 at ~13 tok/s on an M5 Ultra at Q4_K_M, a figure from its published bandwidth model, not a measured run. It needs about 77 GB of unified memory. It is Mistral's 128B dense model, released under the Mistral Modified MIT licence.
Want to run Mistral Medium 3.5 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~13 tok/s |
| Provenance | estimate · how estimates are made |
| Quantization | Q4_K_M |
| Engine | MLX |
| Figure dated | 2026-10 |
| Minimum RAM | 77 GB |
| Parameters | 128B |
| Chip bandwidth | 1228 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 (77 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 |
|---|---|---|---|---|---|---|
| sourced7.7 tok/s | FP8 | MLX | 512 GB | 8,192-token context, 128 generated | machinelearning.apple.com | Apple ML Research: mlx_lm.benchmark -p 8192 -g 128 -b 1 on one Mac Studio, native FP8. |
| estimated13 tok/s | Q4_K_M | MLX | 96 GB | — | LLMCheck estimator | — |
Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-10-17:
MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:
Downloads: Ollama page → · model card →
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
Mistral's dense 128B (Apr 2026) with image input, 256K context and configurable reasoning; self-reported SWE-bench Verified 77.6 (harness not stated). Its modified MIT licence voids all rights for companies above $20M monthly revenue. Q4_K_M is 75 GB, so it needs a 96–128 GB Mac; Apple's MLX research post reports 7.7 tok/s on an M5 Ultra and 4.95 on an M3 Ultra at native FP8 (8K context), and builds should postdate 1 May, when the YaRN config was fixed.
Mistral Modified MIT licence · 128B · 256K context · LLMCheck capability 43/50 · see its leaderboard rank →
Mistral Medium 3.5 needs about 77 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 Mistral Medium 3.5 stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard