Ranking updated on 09/10/2026
The Mac mini M2 / M2 Pro (8–32 GB, 100–200 GB/s) remains an excellent, quiet inference server for 7–13B models in Q4_K_M. Cooled, compact, ready 24/7.
Compare prices for Mac mini M5 Pro (24 GB / 512 GB) from our partner retailers (verified product pages):
Why this choice? Our complete guide to the Mac mini M5 Pro (24 GB / 512 GB) →
Which PC should you choose for your budget? Our picks from €800 to €3,500 →
Affiliate links — QuelLLM may earn a commission on purchases at no extra cost to you, which does not influence the ranking (established independently). As an Amazon Associate, BestLLMfor earns from qualifying purchases.
Dense 8B Apache 2.0, 12 languages including FR, 131k context, GQA 32Q/8KV. MMLU 73.84, HumanEval 85.37. Released April 29, 2026.
# HuggingFace : ibm-granite/granite-4.1-8b
Granite 4.2 8B (IBM): dense Apache 2.0, 128k context, ~4.6 GB Q4 VRAM. Multilingual chat, coding, and reasoning for the enterprise.
ollama pull granite4.2
SFT “thinking” fine-tune of OLMo 3 7B: step-by-step reasoning, 16k context, ~4.2 GB VRAM in Q4. 100% open, Apache 2.0 license.
# HuggingFace : zimplex/olmo3-7b-think-sft-eosfix-16k-3ep-euc
GLM 5.3 (Zhipu): dense 7B specialized in code and reasoning, 128k context, ~4.1 GB VRAM in Q4. Lightweight, runs on a 6–8 GB GPU, MIT license.
ollama pull glm-5.3
Dense 7B 100% open (weights + data + code). Complete transparency for research.
ollama run olmo-3:7b
Hybrid thinking/fast mode. 119 languages, 32k native (131k via YaRN).
ollama run qwen3:8b
Gemma 4 12B (Google): dense multimodal model (text, vision, audio), 256k context, ~7 GB Q4 VRAM. Apache 2.0, multilingual.
# HuggingFace : google/gemma-4-12B
| Rank | Model | Params | Q4 VRAM | Context | License | On Apple M2 (16 GB) |
|---|---|---|---|---|---|---|
| #1 | Granite 4.1 8B Instruct | 8B | 5 GB | 131 072 | Apache 2.0 | 12 tok/s · Q8 |
| #2 | Granite 4.2 8B | 8B | 4.6 GB | 128 000 | Apache 2.0 | 32 tok/s · Q8 |
| #3 | OLMo 3 7B Think (SFT) | 7B | 4.2 GB | 16 000 | Apache 2.0 | 32 tok/s · Q8 |
| #4 | GLM 5.3 7B | 7B | 4.1 GB | 128 000 | MIT | 32 tok/s · Q8 |
| #5 | OLMo 3 7B | 7B | 5 GB | 8 192 | Apache 2.0 | 12 tok/s · Q8 |
| #6 | Qwen 3 8B | 8B | 5 GB | 131 072 | Apache 2.0 | 12 tok/s · Q8 |
| #7 | Gemma 4 12B | 12B | 7 GB | 262 144 | Apache 2.0 | 18 tok/s · Q5_K_M |
Local AI on your Mac, fully explored: unified memory, MLX vs. GGUF, the right model for your chip, Ollama and LM Studio tuned for Apple Silicon.
Free memo
Get the memo VRAM → best coding model → Ollama command (one screen, copy and paste). Then switch to the Copilote Local kit for a setup that actually works.
The Local Copilot kit — the Ollama + Cline + Aider configs are ready to paste, with tuned Modelfiles, troubleshooting, and lifetime online access →No spam. Unsubscribe in 1 click. Your data stays with us (never resold).
Your card → the best coding model to run locally, and the exact Ollama command:
| Your VRAM | Typical GPUs / Macs | Recommended coding model | Command Ollama |
|---|---|---|---|
| 8 GB | RTX 4060 / 3060 · M1-M2 16 GB | Qwen 3.5 9B (Q4, 6.6 GB — 256k context) | ollama run qwen3.5:9b |
| 12 GB | RTX 3060 12 GB / 4070 / 5070 | Qwen 3.5 9B (Q8, 11 GB) or Gemma 4 12B (7.6 GB) | ollama run qwen3.5:9b-q8_0 |
| 16 GB | RTX 5070 Ti / 4080 / 5080 · RX 9070 XT · M4 24 GB | Devstral 24B (Q4, 14 GB) — coding-agent specialist | ollama run devstral:24b |
| 24 GB | RTX 3090 / 4090 · RX 7900 XTX · M4 Pro 48 GB | Qwen 3.8 27B (Q4, 18 GB) — the “close to Copilot” option | ollama run qwen3.8:27b |
| 32 GB | RTX 5090 | Qwen 3.6 35B-A3B (Q4, 23 GB) — fast MoE | ollama run qwen3.6:35b |
| 48 GB+ | Mac M4 Max 64 GB · M2 Ultra 128 GB | Qwen3-Coder 30B-A3B (Q8, 32 GB — 256k context) | ollama run qwen3-coder:30b-a3b-q8_0 |
-base : ollama run qwen2.5-coder:7b-base — it’s still the reference for this specific use case. ⚠️ Qwen 3.8: its reasoning is set very high by default and it “overthinks” simple requests — lower it to low (or turn it off) on first launch. ⚠️ License trap: Codestral 22B = Mistral Non-Production License → prohibited for coding at work. Qwen 3.5/3.8, Gemma 4, and Devstral are Apache 2.0. 💡 Running out of memory? Keep ~1.5 GB of VRAM free for context, or drop down one quantization level.🔌 To connect it to VS Code: Cline (multi-file agent), Aider (CLI) or Tabby/Twinny (FIM autocomplete) — they all connect to Ollama locally. The kit Local Copilot — ready-to-paste configs + tested setup — is available: /copilote-local.
Filter: 1-32B, with Q4_K_M fitting under 22 GB (32 GB M2 Pro maximum). Bonus: 7-13B (M2 Pro peak) and free licenses for shared servers.
Criteria considered:
The scoring is fully transparent: see our methodology for details on VRAM/tokens/sec calculations.
Mac mini M2 8 GB: still relevant in 2026?
Phi-4 Mini 3.8B Q4 or Llama 3.2 3B Q4 will run—but it's tight. Prefer 16 GB minimum. See the Mac mini M2 guide.
Mac mini M2 Pro 32 GB: what’s the sweet spot?
Mistral Nemo 12B Q4 (~7 GB) or Qwen 3 14B Q4 (~8 GB)—22–28 tok/s. Excellent home LLM server for 1–3 simultaneous users via the Ollama API.
M2 Pro vs. M4 Pro for an LLM server?
M4 Pro (273 GB/s) is ~35–40% faster than M2 Pro (200 GB/s) on the same models. If buying new in 2026, you might as well get the M4 Pro. See Mac mini M4.
Quiet Mac mini M2 server setup?
Ollama + Open WebUI on the LAN, port 11434 behind an nginx reverse proxy. Auto-start via launchd. Idle ~10W, under load ~35W. Quieter than an ITX PC.