The best local LLM for a Mac Studio M4 Max (128 GB) is Qwen3.8-Flash-Next at ~45 tok/s (estimated). Its 128 GB fits 93 of the 130 models in the LLMCheck index, up to 320B-class. For everyday chat and coding, Qwen3.8-Flash-Next is the sweet spot.
Considering this Mac?
Mac Studio M5 Max (128GB): build-to-order from Apple · Mac Studio M4 Max on Amazon Renewed → · compare every Mac for local AI →
Ranked by LLMCheck suitability (capability balanced against speed on the M4 Max); 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 | Qwen3.8-Flash-Next raise GPU limit | 125B MoE | Qwen Custom | estimated45 tok/s | 47/50 | |
| 2 | DeepSeek V4 Flash Vision-Exp over GPU limit | 305B MoE | MIT | estimated32 tok/s | 47/50 | |
| 3 | GLM-5.3-Flash over GPU limit | 320B MoE | MIT | estimated23 tok/s | 48/50 | |
| 4 | Qwen 3.6-35B-A3B | 35B MoE | Apache 2.0 | estimated105 tok/s | agent-ready | 38/50 |
| 5 | Inkling-Small | 276B MoE | Apache 2.0 | estimated38 tok/s | agent-ready | 46/50 |
| 6 | DeepSeek V4 Flash raise GPU limit | 284B MoE | MIT | estimated29 tok/s | 47/50 | |
| 7 | KAT-Coder-V2.5 | 35B MoE | Apache 2.0 | community94 tok/s | agent-ready | 39/50 |
| 8 | Nemotron 3.5 Lightning | 30B MoE | OpenMDW | estimated117 tok/s | agent-ready | 36/50 |
| 9 | North Mini Code 1.0 | 30.5B MoE | Apache 2.0 | estimated114 tok/s | agent-ready | 36/50 |
| 10 | Qwen3.8-27B | 27.8B | Apache 2.0 | estimated26 tok/s | agent-ready | 46/50 |
| 11 | Nanbeige4.3-33B | 33.1B | Apache 2.0 | community25 tok/s | agent-ready | 46/50 |
| 12 | Qwen3-235B-A22B over GPU limit | 235B MoE | Apache 2.0 | estimated23 tok/s | 46/50 |
Showing the top 12 of 93 models that fit in 128 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 112 GB this Mac’s GPU can use with the limit raised (76 of the 85 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 96 GB of this Mac’s 128 GB by default on macOS 15 and earlier, and about 107.5 GB on macOS 26 and later. Of the 93 models that fit, 7 need more than that at a short prompt: 2 need a raised limit and are tagged raise GPU limit (Qwen3.8-Flash-Next and DeepSeek V4 Flash only past the safe setting below, as measured runs on this much memory show); 5 need more than even the raised limit and are tagged over GPU limit. sudo sysctl iogpu.wired_limit_mb=114688 raises it to 112 GB, leaving 16 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: Qwen3.8-Flash-Next needs about 120 GB, more than macOS lets the GPU use on this Mac by default (about 96 GB). Measured runs on 128 GB Macs show it loads with the limit raised, past the index’s safe setting (sudo sysctl iogpu.wired_limit_mb=114688, 112 GB), so macOS keeps less than 16 GB: quit other apps first.
The index has no verified Ollama tag for Qwen3.8-Flash-Next, so start from its listing and copy the exact name there: Search the Ollama library → · 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 Qwen3.8-Flash-Next on M4 Max page for its figures and setup.
The models a 128 GB Mac can hold are big files: Qwen3-235B-A22B, the largest that fits here, is about a 126 GB download at the build it needs, and a few models that size fill an internal drive. A fast external Thunderbolt 5 or USB4 SSD keeps a model library within reach: Thunderbolt 5 external SSDs on Amazon →
Amazon affiliate link: as an Amazon Associate, LLMCheck earns from qualifying purchases.
Twice as fast: no Mac in the index runs Qwen3.8-Flash-Next at twice this Mac’s estimated~45 tok/s; the fastest figure is the Mac Studio M1 Ultra (128 GB) at estimated~57 tok/s, about $2,400 refurbished or used: search Amazon Renewed listings →.
For less: no cheaper Mac in the index runs Qwen3.8-Flash-Next at 15+ tok/s.
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.
Apple no longer sells the Mac Studio M4 Max (128 GB) new. A current Mac Studio M5 Max (128 GB) runs the same models with 614 GB/s of memory bandwidth instead of 546 GB/s, so they generate faster. The Mac Studio M5 Max (128 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 M4 Max (128 GB). llmcheck.net. https://llmcheck.net/best-llm/mac-studio-m4-max-128gb/ (updated ). CC BY 4.0.
Qwen3.8-Flash-Next (125B MoE, Qwen Custom) is the best all-round pick at ~45 tok/s (estimated) on the Mac Studio M4 Max. If you want maximum speed, LFM3-1.7B hits ~266 tok/s (estimated); for maximum capability, GLM-5.3-Flash still fits in 128 GB.
About 93 of the 130 models in the LLMCheck index fit in 128 GB of unified memory, from compact models up to GLM-5.3-Flash (320B MoE).
Yes. A dense 70B such as Llama 3.3 70B needs about 44 GB at 4-bit, which fits in 128 GB with room for context; the index puts it at ~12 tok/s (estimated) on this Mac.
128 GB is enough for dense models up to about 128B at 4-bit (the largest in the index that fits is Mistral Medium 3.5), and for mixture-of-experts models such as GLM-5.3-Flash (~23 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.