The best local LLM for a Mac Studio M1 Ultra (64 GB) is Ling-3.0-flash-VL at ~79 tok/s (estimated). Its 64 GB fits 77 of the 130 models in the LLMCheck index, up to 124B-class. For everyday chat and coding, Ling-3.0-flash-VL is the sweet spot.
Considering this Mac?
Mac Studio M5 Ultra (96GB): build-to-order from Apple · Mac Studio M1 Ultra on Amazon Renewed → · compare every Mac for local AI →
Ranked by LLMCheck suitability (capability balanced against speed on the M1 Ultra); the top pick is the best-ranked model that reaches 15 tok/s here, has a standard Mac runtime and fits the GPU memory limit (raised if need be), and slower models are tagged slow. Click a model for its full figures and setup. Every speed carries its provenance mark: most are index estimates from the memory-bandwidth model, a filled square is a published figure and a hollow circle a community run — submit a real run →
| # | Model | Size | License | Speed | 64K context | Capability |
|---|---|---|---|---|---|---|
| 1 | Ling-3.0-flash-VL raise GPU limit | 124B MoE | MIT | estimated79 tok/s | 42/50 | |
| 2 | Nemotron 3.5 Lightning | 30B MoE | OpenMDW | estimated150 tok/s | agent-ready | 36/50 |
| 3 | North Mini Code 1.0 | 30.5B MoE | Apache 2.0 | estimated132 tok/s | agent-ready | 36/50 |
| 4 | KAT-Coder-V2.5 | 35B MoE | Apache 2.0 | estimated99 tok/s | agent-ready | 39/50 |
| 5 | Qwen 3.6-35B-A3B | 35B MoE | Apache 2.0 | estimated105 tok/s | agent-ready | 38/50 |
| 6 | Qwen3.8-27B | 27.8B | Apache 2.0 | estimated38 tok/s | agent-ready | 46/50 |
| 7 | Nanbeige4.3-33B | 33.1B | Apache 2.0 | estimated35 tok/s | agent-ready | 46/50 |
| 8 | GLM-4.7-Flash | 31B MoE | MIT | estimated120 tok/s | agent-ready | 35/50 |
| 9 | Gemma 4 26B-A4B | 26B MoE | Apache 2.0 | estimated120 tok/s | agent-ready | 35/50 |
| 10 | Raon-1 mini preview | 28.8B MoE | Apache 2.0 | estimated135 tok/s | agent-ready | 34/50 |
| 11 | LFM2.5-24B-A2B | 24B MoE | LFM Open | estimated114 tok/s | agent-ready | 35/50 |
| 12 | Qwen 3.6-27B | 27B | Apache 2.0 | estimated38 tok/s | agent-ready | 44/50 |
Showing the top 12 of 77 models that fit in 64 GB. See the full leaderboard or all benchmarks.
Context: “fits” means the weights at a short prompt. Coding agents (Claude Code, OpenCode, Codex CLI) hold 64K tokens or more, and every token adds KV cache: agent-ready marks a model whose weights plus a 64K-token 16-bit KV cache still fit in the 56 GB this Mac’s GPU can use with the limit raised (60 of the 70 models here with a KV figure). That is an estimate from each model’s config.json, not a measurement; a q8 KV cache halves the cache part, and — means the index has no KV figure for the model yet. The GPU memory limit below applies on top.
GPU memory limit: macOS lets the GPU use about 48 GB of this Mac’s 64 GB by default on macOS 15 and earlier, and about 51.8 GB on macOS 26 and later. Of the 77 models that fit, 6 need more than that at a short prompt: 3 need a raised limit and are tagged raise GPU limit; 3 need more than even the raised limit and are tagged over GPU limit. sudo sysctl iogpu.wired_limit_mb=57344 raises it to 56 GB, leaving 8 GB for macOS, until the Mac restarts (sudo sysctl iogpu.wired_limit_mb=0 restores the default). How the limit is read →
GPU memory limit: Ling-3.0-flash-VL needs about 56 GB, more than macOS lets the GPU use on this Mac by default (about 48 GB). Raise the limit first; it lasts until the Mac restarts:
The index has no verified Ollama tag for Ling-3.0-flash-VL, so start from its listing and copy the exact name there: Hugging Face repo → · model card →
GGUF builds run in LM Studio or llama.cpp; MLX builds run in LM Studio or mlx-lm.
Prefer a GUI? LM Studio gives you a one-click download and chat window. For step-by-step help see our Ollama install guide, or open the Ling-3.0-flash-VL on M1 Ultra page for its figures and setup.
Twice as fast: no Mac in the index runs Ling-3.0-flash-VL at twice this Mac’s estimated~79 tok/s; the fastest figure is the Mac Studio M5 Ultra (96 GB) at estimated~89 tok/s, $5,499 new (Apple list price, checked 2026-11-14): build-to-order from Apple (Amazon does not stock this configuration).
For less: the cheapest Mac that still runs Ling-3.0-flash-VL at 15+ tok/s is the Mac Studio M2 Max (64 GB) at estimated~46 tok/s, about $1,600 refurbished or used: search Amazon Renewed listings →.
Speeds are each Mac’s own figure from the index, with its provenance mark. Prices come from data/macs.json: Apple’s list price for a new Mac (dated), an approximate street price for a used or refurbished one. Amazon stock checked 2026-11-18. Amazon links are affiliate links: as an Amazon Associate, LLMCheck earns from qualifying purchases.
The Mac Studio M1 Ultra (64 GB) tops out at Ling-3.0-flash-VL. A current Mac Studio M5 Ultra (96 GB) fits 9 more of the index’s models and reads memory at 1228 GB/s instead of 800 GB/s, so models also generate faster. The Mac Studio M5 Ultra (96 GB) is build-to-order from Apple; Amazon does not stock that configuration.
As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence our rankings.
LLMCheck. (2026). Best Local LLMs for the Mac Studio M1 Ultra (64 GB). llmcheck.net. https://llmcheck.net/best-llm/mac-studio-m1-ultra-64gb/ (updated ). CC BY 4.0.
Ling-3.0-flash-VL (124B MoE, MIT) is the best all-round pick at ~79 tok/s (estimated) on the Mac Studio M1 Ultra. If you want maximum speed, LFM3-1.7B hits ~330 tok/s (estimated); for maximum capability, Qwen3.8-27B still fits in 64 GB.
About 77 of the 130 models in the LLMCheck index fit in 64 GB of unified memory, from compact models up to Ling-3.0-flash-VL (124B MoE).
Yes. A dense 70B such as Llama 3.3 70B needs about 44 GB at 4-bit, which fits in 64 GB with room for context; the index puts it at ~15 tok/s (estimated) on this Mac.
64 GB is enough for dense models up to about 72B at 4-bit (the largest in the index that fits is Qwen 2.5 72B), and for mixture-of-experts models such as Ling-3.0-flash-VL (~79 tok/s (estimated)). As a rule of thumb a 4-bit model needs about 0.57 GB per billion parameters plus ~2 GB, and macOS needs its own share of memory too. Because Apple Silicon uses unified memory, the same pool serves as system RAM and GPU memory.