Best Local LLMs for the iMac M6 (24 GB)

The best local LLM for an iMac M6 (24 GB) is Recursive Flint at ~71 tok/s (estimated), the top-ranked model that reaches 15 tok/s here. Its 24 GB fits 63 of the 130 models in the LLMCheck index, up to 39.8B-class. The most capable, Qwen3.8-27B, runs at 10 tok/s (community run): slow for chat.

Unified memory
24
GB
Mem. bandwidth
170
GB/s
Models that fit
63
of 130
Top speed
estimated132
tok/s

Considering this Mac?
iMac M6 on Amazon → check the listing’s memory · not sure? the Mac Advisor picks a config →

Top 3 picks for the iMac M6 (24 GB)

⭐ Best overall
39.8B MoE · Apache 2.0 · cap 37/50 raise GPU limit
Raise the GPU limit first: sudo sysctl iogpu.wired_limit_mb=20480
estimated71 tok/s
⚡ Fastest
7.9B MoE · MIT · cap 15/50 · agent-ready 64K
estimated132 tok/s
🧠 Most capable (slow)
27.8B · Apache 2.0 · cap 46/50 raise GPU limit
Raise the GPU limit first: sudo sysctl iogpu.wired_limit_mb=20480
community10 tok/s

Every model ranked for an iMac M6 (24 GB)

Ranked by LLMCheck suitability (capability balanced against speed on the M6); 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 →

#ModelSizeLicenseSpeed64K contextCapability
1Recursive Flint raise GPU limit39.8B MoEApache 2.0estimated71 tok/sneeds ~22 GB37/50
2Qwen3.8-27B slow raise GPU limit27.8BApache 2.0community10 tok/sneeds ~24 GB46/50
3Nanbeige4.3-33B slow33.1BApache 2.0estimated7 tok/sneeds ~31 GB46/50
4Qwen 3.6-27B slow raise GPU limit27BApache 2.0estimated9 tok/sneeds ~23 GB44/50
5Qwen 3.6-35B-A3B raise GPU limit35B MoEApache 2.0community59 tok/sneeds ~26 GB38/50
6KAT-Coder-V2.5 over GPU limit35B MoEApache 2.0estimated47 tok/sneeds ~26 GB39/50
7LFM2.5-24B-A2B24B MoELFM Openestimated79 tok/sagent-ready35/50
8Muse Glimmer 30B slow raise GPU limit30BApache 2.0estimated6 tok/sagent-ready42/50
9MiniCPM-V 4.7 35B-A3B over GPU limit35.2B MoEApache 2.0estimated54 tok/sneeds ~25 GB35/50
10Nemotron 3.5 Lightning raise GPU limit30B MoEOpenMDWcommunity45 tok/sagent-ready36/50
11Gemma 4 31B slow raise GPU limit31BApache 2.0community8 tok/sneeds ~30 GB40/50
12Raon-1 mini preview raise GPU limit28.8B MoEApache 2.0estimated58 tok/sagent-ready34/50
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Showing the top 12 of 63 models that fit in 24 GB. See the full leaderboard or all benchmarks.

Estimated figures come from the bandwidth formula; against 163 measured runs its typical error is ±9% for dense models and ±15% for small MoEs (≤40B total). How the error is computed →

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 20 GB this Mac’s GPU can use with the limit raised (33 of the 58 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 17.8 GB of this Mac’s 24 GB by default (macOS 26 and later, the only macOS it runs). Of the 63 models that fit, 23 need more than that at a short prompt: 15 need a raised limit and are tagged raise GPU limit (Qwen 3.6-35B-A3B and Gemma 4 31B only past the safe setting below, as measured runs on this much memory show); 8 need more than even the raised limit and are tagged over GPU limit. sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB, leaving 4 GB for macOS, until the Mac restarts (sudo sysctl iogpu.wired_limit_mb=0 restores the default). How the limit is read →

Quick start: run Recursive Flint on your iMac M6

GPU memory limit: Recursive Flint needs about 20 GB, more than macOS lets the GPU use on this Mac by default (about 17.8 GB). Raise the limit first; it lasts until the Mac restarts:

sudo sysctl iogpu.wired_limit_mb=20480

The fastest way to get started is Ollama. Install it, then pull the model by its tag (checked on ollama.com, 2026-11-14):

brew install ollama

ollama run flint:40b · model card →

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 Recursive Flint on M6 page for its figures and setup.

Same Mac with more memory, and the upgrade path

Upgrade or save: Recursive Flint on other Macs

Same pick, other Macs

Twice as fast: no Mac in the index runs Recursive Flint at twice this Mac’s estimated~71 tok/s; the fastest figure is the Mac Studio M5 Max (36 GB) at community131 tok/s, $2,499 new (Apple list price, checked 2026-11-14): Mac Studio M5 Max (36GB) on Amazon →.

For less: the cheapest Mac that still runs Recursive Flint at 15+ tok/s is the MacBook Air M2 (24 GB) at estimated~49 tok/s, about $850 refurbished or used: search Amazon Renewed listings →. New: the Mac mini M6 (24 GB) at estimated~71 tok/s, $1,099 new (Apple list price, checked 2026-11-14): Mac mini M6 (24GB) on Amazon →.

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.

🛒 Get an iMac M6 for local AI

The iMac M6 (24 GB) runs 63 of the models in the LLMCheck index, led by Recursive Flint. It is sold new by Apple; Amazon stock of the 24 GB configuration is not verified, so check the listing’s memory:

As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence our rankings.

Cite this page

LLMCheck. (2026). Best Local LLMs for the iMac M6 (24 GB). llmcheck.net. https://llmcheck.net/best-llm/imac-m6-24gb/ (updated ). CC BY 4.0.

How to cite LLMCheck →Data: CC BY 4.0Markdown version

FAQ: local LLMs on the iMac M6

What is the best local LLM for an iMac M6 (24 GB)?

Recursive Flint (39.8B MoE, Apache 2.0) is the best all-round pick at ~71 tok/s (estimated) on the iMac M6. If you want maximum speed, Ling-3.0-tiny hits ~132 tok/s (estimated); Qwen3.8-27B is more capable but runs at only 10 tok/s (community run) here.

How many models can an iMac M6 with 24 GB run?

About 63 of the 130 models in the LLMCheck index fit in 24 GB of unified memory, from compact models up to Recursive Flint (39.8B MoE).

Can an iMac M6 run a 70B model?

No. A dense 70B such as Llama 3.3 70B needs about 44 GB at 4-bit; with 24 GB, stick to models like Recursive Flint. For a 70B, look at a 64 GB+ Mac.

Is 24 GB of RAM enough to run LLMs locally?

24 GB is enough for dense models up to about 33B at 4-bit (the largest in the index that fits is Nanbeige4.3-33B), and for mixture-of-experts models such as KAT-Coder-V2.5 (~47 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.

Related