Apple · M6 · Laptop
Best AI Models for MacBook Pro 14" M6 (24 GB)
Runs 9B models well and fits 35B MoE; 14B and 27–31B fit but are slow (13 and 7 tok/s), and 70B doesn't fit in 20.5 GB.
| # | Model | Speed | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB · 34.4 t/s | 34.4 tok/s | Q4_K_M · 16.5 GB | |
| 2 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s | 18.7 tok/s | Q4_K_M · 6.6 GB | |
| 3 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 36.5 t/s | 36.5 tok/s | Q4_K_M · 3.4 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s | 37.6 tok/s | Q4_K_M · 13.1 GB | |
| 5 | LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s | 48.1 tok/s | Q4_K_M · 15.0 GB |
| # | Model | Speed | Coding Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB · 34.4 t/s | 34.4 tok/s | Q4_K_M · 16.5 GB | |
| 2 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s | 37.6 tok/s | Q4_K_M · 13.1 GB | |
| 3 | Q4_K_M · 7.9 GB · 22.5 t/s | 22.5 tok/s | Q4_K_M · 7.9 GB | |
| 4 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s | 18.7 tok/s | overall | Q4_K_M · 6.6 GB |
| 5 | LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s | 48.1 tok/s | Q4_K_M · 15.0 GB |
| # | Model | Speed | Reasoning Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB · 34.4 t/s | 34.4 tok/s | Q4_K_M · 16.5 GB | |
| 2 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s | 18.7 tok/s | Q4_K_M · 6.6 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s | 37.6 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 21.6 t/s | 21.6 tok/s | Q4_K_M · 7.6 GB | |
| 5 | LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s | 48.1 tok/s | Q4_K_M · 15.0 GB |
| # | Model | Speed | Long context Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 18.7 t/s | 18.7 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 36.5 t/s | 36.5 tok/s | Q4_K_M · 3.4 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s | 37.6 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Q4_K_M · 7.9 GB · 22.5 t/s | 22.5 tok/s | Q4_K_M · 7.9 GB | |
| 5 | LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s | 48.1 tok/s | Q4_K_M · 15.0 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 37.6 t/s | 37.6 tok/s | Q4_K_M · 13.1 GB | |
| 2 | LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s | 48.1 tok/s | Q4_K_M · 15.0 GB | |
| 3 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 36.5 t/s | 36.5 tok/s | Q4_K_M · 3.4 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 34.4 t/s | 34.4 tok/s | Q4_K_M · 16.5 GB | |
| 5 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s | 18.7 tok/s | Q4_K_M · 6.6 GB |
The MacBook Pro 14" M6 is a mid-range 24 GB laptop: it runs 9B models well and fits 35B MoE. Among 24 GB machines, only the M5 Pro and M4 Pro write faster. macOS keeps about 3.5 GB, leaving 20.5 GB for models. With 19 TFLOPS it reads long prompts faster than most 24 GB machines: a 4K-token prompt takes 9.4 s. At its $2,199 MSRP it gives 8.5 tok/s per $1,000, 6th of the 8 machines compared here.
MacBook Pro 14" M6 strengths and weaknesses
Strengths
- Runs 35B MoE models: Qwen3.6 35B A3B at 33.5 tok/s in 19.8 GB
Weaknesses
- 70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 20.5 GB usable here
- Slow on large dense models: Qwen3.8 27B at 6.8 tok/s
- Slow prompt reading: A 32K-token prompt on Gemma 4 26B A4B IT waits 1.3 min for the first token
- No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX
Memory for models
20.5 GB of 24 GB70B models need 51.3 GB at Q4, more than the 20.5 GB available. The 32 GB config fits Qwen3.8 27B →Or rent an A100 (80 GB) from $1.10/hr →
Speed per dollar and per watt
On Qwen3.5 9B (9B params) at Q4_K_M. New means a shop price, either a street quote or the maker's own price; used is compared with used. The last two columns are the speed you get per $1,000 of price and per 100 W of power; higher is better. The MacBook Pro 14" M6 has no current new price, so it is shown at its MSRP.
| Machine | New price | tok/s | tok/s per $1,000 | tok/s per 100 W |
|---|---|---|---|---|
Mac Mini M4 Pro24 GB | about $1,599 | 30.0 | 18.8 | 21.4 |
Mac Mini M624 GB | about $1,099 | 18.7 | 17.0 | – |
| about $1,999 | 30.0 | 15.0 | – | |
| about $2,499 | 30.0 | 12.0 | – | |
iMac 24" M624 GB | about $1,699 | 18.7 | 11.0 | – |
MacBook Pro 14" M624 GB | about $2,199 | 18.7 | 8.5 | – |
MacBook Pro 14" M616 GB | about $1,999 | 16.9 | 8.5 | – |
MacBook Pro 14" M632 GB | about $2,399 | 18.7 | 7.8 | – |
| Machine | Used price | tok/s | tok/s per $1,000 | tok/s per 100 W |
|---|---|---|---|---|
RTX 409024 GBBest used value | about $3,000 | 103 | 34.3 | 22.9 |
RTX 509032 GB | about $7,000 | 183 | 26.2 | 31.8 |
Mac Studio M4 Max36 GB | about $2,000 | 45.1 | 22.6 | 31.1 |
Cost per token: the MacBook Pro 14" M6 against 16–36 GB machines and GPUs
On Qwen3.5 9B (9B params, Q4_K_M, 4K context). Speed, cost per token and power per token depend on the model.
- Machine, MSRP
- $7.46
- Power
- not published
Renting costs as much as buying after ≈4,700 hours (≈3.2 years at 4 h a day).
Each dot is a machine or GPU; hover or tap it for its numbers, click to open it. Machines without a price for the chosen basis are left out. Machines without a published power figure are left out of Per watt and costed without power. How we calculate cost per token
Other memory sizes of the same machine first, then machines and GPUs people weigh against it, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.
Output speed depends on memory bandwidth (170 GB/s). Grey rows need more than the 20.5 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB18.7tok/s
- 14BQwen3 14B · Q4_K_M · 11.9 GB12.5tok/s
- 6.8tok/s
- 33.5tok/s
- 70BLlama 3.3 70B Instruct · not at 4-bitneeds 51.3 GB
- 120B MoEGPT OSS 120B · not at 4-bitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
Chip generations: writing vs compute
M1 → M5Writing speed follows memory bandwidth and barely moved: 7.5 to 16.9 tok/s since the M1. Compute, which sets how fast prompts are read, grew 3.1×. Indexed to the M1; speeds on Qwen3.5 9B, same 16 GB.
All 322 models on the MacBook Pro 14" M6
Featured onlyBest quant that fits in 20.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
Dots.mocrVision | Q4_K_M | 2.6 GB | 54.6 t/s | 131K | A81, Runs well | |
Qwen AgentWorld 35B A3BChatFunctions | Q4_K_S | 20.0 GB | 40.6 t/s | 262K | B49, Decent | |
QwQ 32BChatReasoningFunctions | IQ3_M | 19.3 GB | 7.6 t/s | 41K | D24, Barely runs | |
Medgemma 1.5 4B ITVision | Q4_K_M | 5 GB | 41.9 t/s | — | A76, Runs well | |
Qwen3 4BChatFunctions | Q4_K_M | 4.2 GB | 41.0 t/s | 41K | A75, Runs well | |
Llama 3.2 1B InstructChatFunctions | Q4_K_M | 2.3 GB | 145.1 t/s | 131K | S97, Runs great | |
Ministral 8B Instruct 2410ChatFunctions | Q4_K_M | 7.5 GB | 22.0 t/s | 33K | B62, Decent | |
Qwen3.5 9B BaseVision | Q4_K_M | 6.6 GB | 18.7 t/s | 262K | B58, Decent | |
Granite Docling 258MVisionChatCodeMath | Q4_K_M | 0.6 GB | 238.0 t/s | 8K | S100, Runs great | |
Qwen3 VL 2B InstructVisionFunctions | Q4_K_M | 3.5 GB | 65.7 t/s | 262K | S85, Runs great | |
Granite 4.1 8BChatFunctions | Q4_K_M | 8.3 GB | 20.1 t/s | 131K | B60, Decent | |
Qianfan OCRVision | Q4_K_M | 4.7 GB | 35.7 t/s | 33K | A73, Runs well | |
Llava 1.5 7B HFVision | Q4_K_M | 5.0 GB | 25.5 t/s | 4K | A66, Runs well | |
| Q4_K_M | 7.3 GB | 22.1 t/s | 131K | B62, Decent | ||
Llama 3.2 11B Vision InstructVisionFunctions | Q4_K_M | 9.8 GB | 16.9 t/s | — | B56, Decent |
Specs
- Chip
- M6
- CPU cores
- 12
- GPU cores
- 12
- Unified memory
- 24 GB
- For models
- 20.5 GB (macOS keeps 3.5 GB)
- Memory bandwidth
- 170 GB/s
- FP16 (dense)
- 19.2 TFLOPS
- Neural Engine
- 76 TOPS
- Released
- 2026-11-06
- MSRP
- $2,199
MacBook Pro 14" M6 FAQ
Is the MacBook Pro 14" M6 (24 GB) worth it for local LLMs in 2026?
At its $2,199 MSRP it gives 8.5 tok/s per $1,000 on Qwen3.5 9B, 6th of the 8 machines compared here. It runs 9B models well and fits 35B MoE; 14B and 27–31B fit but are slow (13 and 7 tok/s), and 70B doesn't fit in 20.5 GB.
How much memory is available for AI on the MacBook Pro 14" M6 (24 GB)?
About 20.5 GB of the 24 GB. macOS keeps roughly 3.5 GB for itself and other apps.
What is the largest model the MacBook Pro 14" M6 (24 GB) can run?
Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at IQ4_XS it uses 19.8 GB, 97% of the available memory, and runs at about 33.5 tok/s.
Can the MacBook Pro 14" M6 (24 GB) run Gemma 4 26B A4B IT?
Yes. Gemma 4 26B A4B IT fits at Q4_K_M, using 16.5 GB of the 20.5 GB available, and it is the best model that runs well on this machine.
Can the MacBook Pro 14" M6 (24 GB) run 70B models?
No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 20.5 GB available.
How long does the MacBook Pro 14" M6 (24 GB) take to read a long prompt?
On Gemma 4 26B A4B IT, about 9.4 s for a 4K-token prompt and 75 s for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the MacBook Pro 14" M6?
An RTX 5090 (32 GB) rents from $0.47/hr. Renting costs as much as buying after ≈4,700 hours (≈3.2 years at 4 h a day).