Mac mini M1 · 16 GB unified
Apple · Mac mini · 2020
117 text models run well · 68 GB/s bandwidth
Models on this hardware
Start here
File Q4_K_M · 0.8 GB · bartowski/Llama-3.2-1B-Instruct-GGUF · What is Q4?
Memory Needs ~1 GB · ~5 GB on Mac mini 2020 · M1 · 16 GB unified, including ~4 GB the system keeps
ollama run hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M- Install Ollama
- Run the command above
- Ask:
Explain what a context window is, in two sentences.
File Q4_K_M · 2.2 GB · ibm-granite/granite-4.2-3b-GGUF · What is Q4?
Memory Needs ~3 GB · ~7 GB on Mac mini 2020 · M1 · 16 GB unified, including ~4 GB the system keeps
ollama run hf.co/ibm-granite/granite-4.2-3b-GGUF:Q4_K_M- Install Ollama
- Run the command above
- Ask:
Explain what a context window is, in two sentences.
File Q4_K_M · 5.3 GB · ibm-granite/granite-4.2-8b-GGUF · What is Q4?
Memory Needs ~6 GB · ~10 GB on Mac mini 2020 · M1 · 16 GB unified, including ~4 GB the system keeps
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q4_K_M- Install Ollama
- Run the command above
- Ask:
Explain what a context window is, in two sentences.
Text
Text · LMArena
rating · higher is better
- Color = publisher
Source: LMArena 2026-10-22 · collected 2026-10-25 · dataset · CC BY 4.0 · Models without a rating are left out, not scored as zero.
| Granite 4.2 3BQ4 · published params · source | 1,290 ± 12 | ~7 GB | Q4 · published params |
|---|---|---|---|
| Granite 4.2 8BQ4 · published params · source | 1,290 ± 11 | ~10 GB | Q4 · published params |
| Phi-4Q4 · published params · source | 1,256 ± 5 | ~15 GBTight fit: Needs ~15 GB: runs well, about 1 GB left beyond the system reserve | Q4 · published params |
| Llama 3.1 8B InstructQ4 · published params · source | 1,211 ± 4 | ~10 GB | Q4 · published params |
| Llama 3.2 3B InstructQ4 · published params · source | 1,167 ± 8 | ~7 GB | Q4 · published params |
| Llama 3.2 1B InstructQ4 · published params · source | 1,111 ± 8 | ~5 GB | Q4 · published params |
| Qwen3 8BQ4 · published params · source | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | Q4 · published params |
| Qwen3.5 9BQ4 · published params · source | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | Q4 · published params |
No model within 16 GB has a LiveBench score, so the table has no LiveBench column. LMArena ratings in this table: LMArena 2026-10-22 · collected 2026-10-25 · dataset · CC BY 4.0
Tight fit: it runs, but leaves less than 1.6 GB free beyond the 4 GB the system keeps (the memory figure already includes that reserve).
Every reviewed text model here 21
Every one that runs here, well or slowly, scored or not; 6 of 21 have a LiveBench or LMArena result. Run well first, then tight fits, then slow; within each, by Hub downloads over 30 days, read 2026-10-25, not by quality.
| Qwen3 8B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | 5.0 | Apache 2.0 | 8.1M |
|---|---|---|---|---|---|---|
| Qwen3.5 9B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | 5.7 | Apache 2.0 | 6.1M |
| Llama 3.1 8B Instruct | Not in LiveBench 2026-06-25 | 1,211 | ~10 GB | 4.9 | Llama 3.1 | 4.8M |
| Qwen3 1.7B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~6 GB | 1.1 | Apache 2.0 | 4.1M |
| Gemma 4 E4B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~10 GB | 5.0 | Apache 2.0 | 4M |
| Llama 3.2 1B Instruct | Not in LiveBench 2026-06-25 | 1,111 | ~5 GB | 0.8 | Llama 3.2 | 3.5M |
| Gemma 4 E2B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~8 GB | 3.1 | Apache 2.0 | 3M |
| Qwen3 4B Instruct 2507 | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~7 GB | 2.5 | Apache 2.0 | 2.6M |
| Gemma 4 12B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~13 GB | 7.1 | Apache 2.0 | 1.7M |
| Llama 3.2 3B Instruct | Not in LiveBench 2026-06-25 | 1,167 | ~7 GB | 2.0 | Llama 3.2 | 1.1M |
| SmolLM3 3B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~7 GB | 1.9 | Apache 2.0 | 718.7K |
| DeepSeek R1 0528 Qwen3 8B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | 5.0 | MIT | 355.8K |
| Phi-4 mini | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~7 GB | 2.5 | MIT | 342.8K |
| Olmo 3 7B Instruct | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~10 GB | 4.5 | Apache 2.0 | 262.5K |
| Ministral 3 3B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~7 GB | 2.1 | Apache 2.0 | 87.4K |
| Ministral 3 8B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | 5.2 | Apache 2.0 | 79.4K |
| Granite 4.2 8B | Not in LiveBench 2026-06-25 | 1,290 | ~10 GB | 5.3 | Apache 2.0 | 78.3K |
| Granite 4.2 3B | Not in LiveBench 2026-06-25 | 1,290 | ~7 GB | 2.2 | Apache 2.0 | 39.8K |
| Qwen3 14B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~16 GBTight fit | 9.0 | Apache 2.0 | 10.4M |
| Phi-4 | Not in LiveBench 2026-06-25 | 1,256 | ~15 GBTight fit | 8.0 | MIT | 368.3K |
| Ministral 3 14B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~15 GBTight fit | 8.2 | Apache 2.0 | 126.5K |
With 24 GB you also run… 2
The next memory size on this ladder runs these well. Figures are the requirement on this hardware type.
- gpt-oss-20bOpenAI~20 GBQ4 · published params
- Devstral Small 2 24BMistral~22 GBQ4 · published params
Adjust the estimate: quantization, context, reserve
Vision
Vision · LMArena
rating · higher is better
- Color = publisher
Source: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0 · Models without a rating are left out, not scored as zero.
| Molmo2-8BQ4 · Hugging Face count · source | 1,112 ± 20 | ~11 GB | Q4 · Hugging Face count |
|---|---|---|---|
| Qwen2-VL-7B-InstructQ4 · Hugging Face count · source | 1,031 ± 11 | ~11 GB | Q4 · Hugging Face count |
| Molmo-7B-D-0924Q4 · Hugging Face count · source | 994 ± 14 | ~10 GB | Q4 · Hugging Face count |
| Llama-3.2-11B-Vision-InstructQ4 · Hugging Face count · source | 993 ± 11 | ~13 GB | Q4 · Hugging Face count |
| MiniCPM-V-2_6Q4 · Hugging Face count · source | 962 ± 16 | ~11 GB | Q4 · Hugging Face count |
| Phi-3.5-vision-instructQ4 · Hugging Face count · source | 919 ± 16 | ~8 GB | Q4 · Hugging Face count |
| Gemma 4 12BQ4 · published params · source | Not on the LMArena vision leaderboard of 2026-10-19 | ~13 GB | Q4 · published params |
| Qwen3.5 9BQ4 · published params · source | Not on the LMArena vision leaderboard of 2026-10-19 | ~11 GB | Q4 · published params |
LMArena ratings in this table: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0
Tight fit: it runs, but leaves less than 1.6 GB free beyond the 4 GB the system keeps (the memory figure already includes that reserve).
12 more vision models in the catalog have no usable memory figure or parameter count for this profile. Browse Vision models
Image
Image · Prompt alignment · GenEval
0–1 · higher is better
Source: GenEval · 2023 · reviewed 2026-10-05 · Published quality in the original benchmark preset; not measured on this hardware.
| Stable Diffusion XL 1.0Platform path documented · Apple Core ML · source | 0.55 | Not on the LMArena text-to-image leaderboard of 2026-10-07 | Documented path without a memory figure | Platform path documented |
|---|---|---|---|---|
| Stable Diffusion 1.5Platform path documented · Apple Core ML · source | 0.43 | Not on the LMArena text-to-image leaderboard of 2026-10-07 | Documented path without a memory figure | Platform path documented |
| FLUX.2 [klein] 4B16-bit est. · params · source | No comparable published result | 1,030 ± 3 | ~12 GB | 16-bit est. · params |
| FLUX.2 [klein] Base 4B16-bit est. · params · source | No comparable published result | Arena rated flux-2-klein-4b; this entry is the undistilled Base checkpoint | ~12 GB | 16-bit est. · params |
| TRELLIS.2-4B16-bit est. · params · source | No comparable published result | Not reviewed for LMArena | ~12 GB | 16-bit est. · params |
| Stable Diffusion 3.5 MediumConditional path · source | No comparable published result | Not on the LMArena text-to-image leaderboard of 2026-10-07 | ~10 GB | Conditional path |
| Illustrious-xl-early-release-v016-bit est. · params · source | No comparable published result | Not reviewed for LMArena | ~9 GB | 16-bit est. · params |
| Kolors16-bit est. · params · source | No comparable published result | Not reviewed for LMArena | ~9 GB | 16-bit est. · params |
LMArena ratings in this table: LMArena 2026-10-07 · collected 2026-10-25 · dataset · CC BY 4.0
With 24 GB you also run… 23
The next memory size on this ladder. Figures are the requirement on this hardware type.
- Kandinsky-5.0-T2I-Lite-sft-Diffuserskandinskylab~17 GB16-bit est. · params
- LongCat ImageMeituan~17 GB16-bit est. · params
- Ming-Image-0.1-DesigninclusionAI~17 GB16-bit est. · params
- Z-ImageTongyi-MAI~17 GB16-bit est. · params
- Janus ProDeepSeek~19 GB16-bit est. · params
- OmniGen V2VectorSpaceLab~19 GB16-bit est. · sum of parts
- Qwen-Image-2.1Qwen~20 GB16-bit est. · params
- Qwen-Image-2.1-TurboQwen~20 GB16-bit est. · params
- ERNIE ImageBaidu~22 GB16-bit est. · params
- ERNIE Image TurboBaidu~22 GB16-bit est. · params
- FIBOBria~22 GB16-bit est. · params
- FIBO LiteBria~22 GB16-bit est. · params
- Fibo-1.5briaai~22 GB16-bit est. · params
- Fibo-Editbriaai~22 GB16-bit est. · params
- HiDream-O1-ImageHiDream~22 GB16-bit est. · params
- HiDream-O1-Image-DevHiDream~22 GB16-bit est. · params
- Infinity 8BByteDance~22 GB16-bit est. · params
- Stable Diffusion 3.5 LargeStability AI~22 GB16-bit est. · params
- Stable Diffusion 3.5 Large TurboStability AI~22 GB16-bit est. · params
- FLUX.2 [klein] 9BBlack Forest Labs~24 GB16-bit est. · params
- FLUX.2 [klein] Base 9BBlack Forest Labs~24 GB16-bit est. · params
- FLUX.2-klein-9b-kvblack-forest-labs~24 GB16-bit est. · params
- HiDream-O1-Image-Dev-2604HiDream-ai~24 GB16-bit est. · params
17 more image models in the catalog have no usable memory figure or parameter count for this profile. Browse Image models
Video
| CogVideoX-5b-I2V16-bit est. · params · source | ~16 GB | 16-bit est. · params |
|---|---|---|
| CogVideoX1.5-5B16-bit est. · params · source | ~16 GB | 16-bit est. · params |
| CogVideoX1.5-5B-I2V16-bit est. · params · source | ~16 GB | 16-bit est. · params |
| CogVideoX-5B16-bit est. · params · source | ~14 GB | 16-bit est. · params |
| Wan2.2-TI2V-5B16-bit est. · params · source | ~14 GB | 16-bit est. · params |
| Wan2.2-TI2V-5B-Diffusers16-bit est. · params · source | ~14 GB | 16-bit est. · params |
| SANA-Video_2.0_5B_720p16-bit est. · params · source | ~13 GB | 16-bit est. · params |
| Kandinsky-6.0-Lite-distill-5s-Diffusers16-bit est. · params · source | ~10 GB | 16-bit est. · params |
How this list works Documented execution paths on this hardware first, then publisher minimums (CUDA or Apple MPS).
With 24 GB you also run… 1
The next memory size on this ladder. Figures are the requirement on this hardware type.
- HunyuanVideo-1.5tencent~22 GB16-bit est. · params
21 more video models in the catalog have no usable memory figure or parameter count for this profile. Browse Video models
Audio
Audio · Word error rate · Open ASR
% · lower is better
Source: Word error rate · Open ASR · reviewed 2026-10-20 · Published quality in the original benchmark preset; not measured on this hardware.
| Whisper large-v3-turboPlatform path documented · whisper.cpp / Metal · source | 7.83 | Documented path without a memory figure | Platform path documented |
|---|---|---|---|
| Whisper large-v3Platform path documented · whisper.cpp / Metal · source | 7.44 | Documented path without a memory figure | Platform path documented |
| GaussianMind16-bit est. · params · source | No comparable published result | ~16 GB | 16-bit est. · params |
| higgs-tts-2-3b-base16-bit est. · params · source | No comparable published result | ~16 GB | 16-bit est. · params |
| Phi-4-multimodal-instruct16-bit est. · params · source | No comparable published result | ~16 GB | 16-bit est. · params |
| acestep-v15-xl-turbo16-bit est. · params · source | No comparable published result | ~14 GB | 16-bit est. · params |
| higgs-tts-3-4b16-bit est. · params · source | No comparable published result | ~14 GB | 16-bit est. · params |
| acestep-5Hz-lm-4B16-bit est. · params · source | No comparable published result | ~13 GB | 16-bit est. · params |
With 24 GB you also run… 10
The next memory size on this ladder. Figures are the requirement on this hardware type.
- omniASR-W2V-7Bfacebook~18 GB16-bit est. · params
- MiMo-V2.5-ASRXiaomiMiMo~21 GB16-bit est. · params
- moshiko-pytorch-bf16kyutai~21 GB16-bit est. · params
- audio-flamingo-3-hfnvidia~22 GB16-bit est. · params
- Llasa-8BHKUSTAudio~23 GB16-bit est. · params
- MOSS-TTS-v1.5OpenMOSS-Team~23 GB16-bit est. · params
- personaplex-7b-v1nvidia~23 GB16-bit est. · params
- Qwen2-Audio-7B-InstructQwen~23 GB16-bit est. · params
- VibeVoice-ASRmicrosoft~23 GB16-bit est. · params
- VibeVoice-ASR-Streaming-7Bmicrosoft~23 GB16-bit est. · params
35 more audio models in the catalog have no usable memory figure or parameter count for this profile. Browse Audio models
Embeddings
Embeddings · MTEB (Multilingual, v2) · mean(task)
0–100 · higher is better
- Color = publisher
| Qwen3-Embedding 8B8-bit · published params · source | 70.6 | ~12 GB | 8-bit · published params |
|---|---|---|---|
| Qwen3-Embedding 4B8-bit · published params · source | 69.5 | ~7 GB | 8-bit · published params |
| Harrier OSS v1 (0.6B)8-bit · published params · source | 69.0 | ~3 GB | 8-bit · published params |
| Qwen3-Embedding 0.6B8-bit · published params · source | 64.3 | ~3 GB | 8-bit · published params |
| Multilingual E5 Large Instruct8-bit · published params · source | 63.2 | ~3 GB | 8-bit · published params |
| EmbeddingGemma 28-bit · published params · source | 61.4 | ~3 GB | 8-bit · published params |
| EmbeddingGemma (300M)8-bit · published params · source | 61.1 | ~3 GB | 8-bit · published params |
| BGE-M38-bit · published params · source | 59.6 | ~3 GB | 8-bit · published params |
With 24 GB you also run… 1
The next memory size on this ladder runs these well. Figures are the requirement on this hardware type.
- KaLM-Embedding-Gemma3-12B-2511tencent~17 GB8-bit · Hub count
Runs well within 16 GB of unified memory · planning estimates, not measured speed
Measurements
Published tokens per second, exactly as measured; never estimated.
| Llama 7B Q4_0 (llama-bench reference model) | 14.15 | Q4_0 | Metal | llama.cpp Apple Silicon summary · community result |
|---|
Specifications
22 sourced fields; the source is named once per group, and a field from another source links to it. Official specifications
Marker: the lightest text model that does not run well here but runs well with 24 GB. No text model that runs well here has a LiveBench score. Q4 planning estimate, not a measured fit.
Selected configuration
Latest check · Manufacturer source
- Memory capacity
- 16 GB
- Memory type
- 16 GB unified
- Chip / processor
- Apple M1 · 8-core CPU / 8-core GPU
- CPU
- Apple M1
- CPU cores
- 8
- GPU
- Apple M1 GPU
- GPU cores
- 8
Family specification
Latest check · Manufacturer source
- Introduced
- 2020
- Storage options (family)
- 256 GB · 512 GB · 1 TB · 2 TB SSD
- Ports
- 2 × Thunderbolt 3 / USB4 · 2 × USB-A · HDMI · Ethernet · 3.5 mm
- Maximum continuous power (specification)
- 150 W
- Wi-Fi
- Wi-Fi 6 (802.11ax)
- Bluetooth
- Bluetooth 5.0
- Dimensions
- 19.7 × 19.7 × 3.6 (W × D × H)
- Maximum simultaneous displays
- 2
- Neural Engine cores
- 16
- Operating system
- macOS
- Maximum Thunderbolt rate
- 40 Gb/s
- Weight
- 1.2 kg
Apple lists 16 GB as the M1 mini's configurable memory option. It retains the M1 8-core CPU / 8-core GPU; the OS and applications share the memory pool. This profile estimates capacity only and does not claim measured speed or current runtime compatibility.
Photo: Official manufacturer image. · Manufacturer source
Memory bandwidth is not measured model speed; verify runtime and checkpoint compatibility. Hardware specification reviewed: 2026-10-13.
How estimates work
- Candidates
- Reviewed pages use published parameter counts; automatic text candidates use official repository tensor counts (packed quantized weights and unsupported architectures excluded).
- Planning
- Q4 weights + 20% allowance + reserve: 25% of unified or system memory (at least 2 GB, at most 8 GB; 4 GB here) or 2 GB per dedicated GPU. Adjustable in “Adjust the estimate”. No KV cache is calculated from context.
- Fit tiers
- Runs well: the estimate fits the fast memory (VRAM, or unified memory within the macOS GPU share). Runs slowly: within the machine's memory but outside the fast part; a graphics card offloads layers to PC RAM (the listed RAM, or 32 GB assumed). Doesn't run: above both. Tiers are planning estimates, never a speed.
- Vision
- Vision-language models use the Q4 planning estimate from the parameter count (published by the model page, or read from Hugging Face). Classic vision models (classify, detect, segment) use a 16-bit estimate. No vision benchmark is tracked, so rows carry no score.
- Media and embeddings
- Media rows use documented execution paths (exact hardware or platform) and publisher minimums; a published requirement above this memory moves a model to the next tier. Without either, a 16-bit estimate from the published parameter count (× 1.2 + 2 GB), labelled as such. Embeddings use 8-bit weights + 20% + 2 GB.
Local AI basics: parameters, Q4 and memory · Full model catalog · Data and methodology
Alternatives
Other machines on the same memory ladder (unified memory); each page lists the models that fit it.
Also 16 GB 8
- iMac 24-inch · M4 · 8-core CPU / 8-core GPU · 16 GB unified
- Mac mini M2 · 16 GB unified
- Mac mini M4 · 16 GB unified
- Mac mini M6 · 16 GB unified
- MacBook Air 13-inch M4 · 16 GB unified
- MacBook Air 13-inch M5 · 16 GB unified
- MacBook Air 15-inch · M5 · 10-core CPU / 10-core GPU · 16 GB unified
- MacBook Pro 14-inch (M5) · M5 · 10-core CPU / 10-core GPU · 16 GB unified
Less memory · 8 GB 2
More memory · 24 GB 8
- Mac mini M2 · 24 GB unified
- Mac mini M4 · 24 GB unified
- Mac mini M4 Pro · 24 GB unified
- Mac mini M5 Pro · 15-core CPU / 16-core GPU · 24 GB unified
- Mac mini M6 · 24 GB unified
- MacBook Air 13-inch M4 · 24 GB unified
- MacBook Air 13-inch M5 · 24 GB unified
- MacBook Pro 14-inch · M5 Pro · 18-core CPU / 20-core GPU · 24 GB unified
