Ranking updated on 09/10/2026
The MacBook Pro M1 Pro / Max (16–64 GB, 200–400 GB/s) is 4 years old but remains usable. 7–32B models in Q4 are comfortable; 70B in Q3 is workable on the 64 GB Max.
Compare prices for MacBook Pro M5 Pro — 24 GB / 1 TB from our partner retailers (verified product pages):
Which PC should you choose for your budget? Our picks from €800 to €3,500 →
Affiliate links — BestLLMfor may earn a commission from purchases at no extra cost to you, which does not influence the independently determined ranking. As an Amazon Associate, BestLLMfor earns from qualifying purchases.
MoE variant of Gemma 4. 26B/4B active. Full multimodal (text+image+audio).
ollama run gemma4:26b
First open Apache 2.0 dLLM: MoE 16B/1B + 6.2B diffusion decoder. Unified text+vision. Released April 22, 2026.
# HuggingFace : inclusionAI/LLaDA2.0-Uni (Flash Attn 2 + CUDA 12.4 requis)
Dense multimodal 27B released April 22, 2026. 262k ctx (1M YaRN). SWE-bench Verified 77.2%.
ollama run qwen3.6:27b
Qwen 3.8 27B: dense multimodal (text + vision), 262k context, ~16 GB Q4 VRAM (18 GB of Ollama weights). Apache 2.0, agentic coding and vision.
ollama run qwen3.8:27b
GLM-4.7-Flash (MoE 31B, ~3B active): the best code/VRAM ratio in the 30B class. MIT, 128k ctx, very fast on 3090/4090.
ollama run glm-4.7-flash
Dense 31B multimodal (text+image+audio). 140+ languages, 256k context. #3 open model on Chatbot Arena.
ollama run gemma4:31b
Dense 30B Apache 2.0, 12 languages including FR, 131k ctx, GQA 32Q/8KV. OpenAI-compatible tool calling. Released April 29, 2026.
ollama run granite4.1:30b
| Rank | Model | Params | Q4 VRAM | Context | License | On Apple M1 (16 GB) |
|---|---|---|---|---|---|---|
| #1 | Gemma 4 26B-A4B MoE | 26B | 16 GB | 128 000 | Apache 2.0 | ✗ |
| #2 | LLaDA 2.0 Uni 16B | 16B | 18 GB | 8 192 | Apache 2.0 | ✗ |
| #3 | Qwen 3.6 27B | 27B | 16 GB | 262 144 | Apache 2.0 | ✗ |
| #4 | Qwen 3.8 27B | 27B | 16 GB | 262 144 | Apache 2.0 | ✗ |
| #5 | GLM 4.7 Flash | 31B | 19 GB | 128 000 | MIT | ✗ |
| #6 | Gemma 4 31B | 31B | 18 GB | 256 000 | Apache 2.0 | ✗ |
| #7 | Granite 4.1 30B Instruct | 30B | 17 GB | 131 072 | Apache 2.0 | ✗ |
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: 3-70B models whose Q4_K_M fits under 40 GB. Bonus: 7-32B (peak M1 Max). We remain cautious about 70B (limited bandwidth vs. M3/M4).
Criteria considered:
The scoring is fully transparent: see our methodology for details on VRAM/tokens/sec calculations.
16 GB MBP M1 Pro in 2026: is it worth it?
Yes for 7-8B: Mistral 7B Q4, Qwen 3 8B Q4 at 22-28 tok/s. See the M1 MacBook Pro guide.
Can an MBP M1 Max 64 GB run a 70B model?
Yes, in Q3_K_M (~32 GB) at 6–9 tok/s — usable for long-form content, but slow for interactive chat. Q4 (~40 GB) fits, but is slower.
M1 Pro vs. M1 Max for 32B?
M1 Pro (200 GB/s) ≈ 12 tok/s on Mistral Small 24B Q4. M1 Max (400 GB/s) ≈ 22 tok/s. The Max doubles memory bandwidth, and the difference is noticeable.
Should you upgrade to M4?
If the M1 Max 64 GB still holds up, no. Otherwise, the M4 Pro 48 GB offers 273 GB/s + a newer Neural Engine — better performance per watt. See M4 MacBook Pro.
Prices in euros (€) are French market prices including VAT, checked by QuelLLM. US prices differ: the Amazon buttons show the current US price.