MacBook Air 13-inch M5 · 24 GB unified
Apple · MacBook Air 13-inch · 2026
633 text models run well · 153 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 · ~7 GB on MacBook Air 13-inch 2026 · M5 · 24 GB unified, including ~6 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 · ~9 GB on MacBook Air 13-inch 2026 · M5 · 24 GB unified, including ~6 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 · ~12 GB on MacBook Air 13-inch 2026 · M5 · 24 GB unified, including ~6 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.
| gpt-oss-20bQ4 · published params · source | 1,317 ± 6 | ~22 GBTight fit: Needs ~22 GB: runs well, about 2 GB left beyond the system reserve | Q4 · published params |
|---|---|---|---|
| Granite 4.2 3BQ4 · published params · source | 1,290 ± 12 | ~9 GB | Q4 · published params |
| Granite 4.2 8BQ4 · published params · source | 1,290 ± 11 | ~12 GB | Q4 · published params |
| Phi-4Q4 · published params · source | 1,256 ± 5 | ~17 GB | Q4 · published params |
| Llama 3.1 8B InstructQ4 · published params · source | 1,211 ± 4 | ~12 GB | Q4 · published params |
| Llama 3.2 3B InstructQ4 · published params · source | 1,167 ± 8 | ~9 GB | Q4 · published params |
| Llama 3.2 1B InstructQ4 · published params · source | 1,111 ± 8 | ~7 GB | Q4 · published params |
| Qwen3 14BQ4 · published params · source | Not on the LMArena text leaderboard of 2026-10-22 | ~18 GB | Q4 · published params |
No model within 24 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 2.4 GB free beyond the 6 GB the system keeps (the memory figure already includes that reserve).
Every reviewed text model here 23
Every one that runs here, well or slowly, scored or not; 7 of 23 have a LiveBench or LMArena result. Run well first, then tight fits, then slow; within each, by Hub downloads over 30 days, read 2026-11-19, not by quality.
| Qwen3 14B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~18 GB | 9.0 | Apache 2.0 | 13.2M |
|---|---|---|---|---|---|---|
| Qwen3.5 9B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~13 GB | 5.7 | Apache 2.0 | 6.5M |
| Qwen3 8B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~13 GB | 5.0 | Apache 2.0 | 6.1M |
| Gemma 4 E4B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~12 GB | 5.0 | Apache 2.0 | 4.4M |
| Llama 3.1 8B Instruct | Not in LiveBench 2026-06-25 | 1,211 | ~12 GB | 4.9 | Llama 3.1 | 4.1M |
| Gemma 4 E2B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~10 GB | 3.1 | Apache 2.0 | 2.8M |
| Qwen3 4B Instruct 2507 | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~9 GB | 2.5 | Apache 2.0 | 2.8M |
| Qwen3 1.7B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~8 GB | 1.1 | Apache 2.0 | 2.7M |
| Gemma 4 12B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~15 GB | 7.1 | Apache 2.0 | 1.6M |
| Llama 3.2 1B Instruct | Not in LiveBench 2026-06-25 | 1,111 | ~7 GB | 0.8 | Llama 3.2 | 1.3M |
| Llama 3.2 3B Instruct | Not in LiveBench 2026-06-25 | 1,167 | ~9 GB | 2.0 | Llama 3.2 | 823.8K |
| DeepSeek R1 0528 Qwen3 8B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~13 GB | 5.0 | MIT | 523.8K |
| Phi-4 mini | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~9 GB | 2.5 | MIT | 301.1K |
| Ministral 3 14B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~17 GB | 8.2 | Apache 2.0 | 207.6K |
| Phi-4 | Not in LiveBench 2026-06-25 | 1,256 | ~17 GB | 8.0 | MIT | 199.5K |
| SmolLM3 3B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~9 GB | 1.9 | Apache 2.0 | 185.3K |
| Olmo 3 7B Instruct | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~12 GB | 4.5 | Apache 2.0 | 133.1K |
| Ministral 3 8B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~13 GB | 5.2 | Apache 2.0 | 90.7K |
| Ministral 3 3B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~9 GB | 2.1 | Apache 2.0 | 72.5K |
| Granite 4.2 8B | Not in LiveBench 2026-06-25 | 1,290 | ~12 GB | 5.3 | Apache 2.0 | 59.5K |
| Granite 4.2 3B | Not in LiveBench 2026-06-25 | 1,290 | ~9 GB | 2.2 | Apache 2.0 | 40.8K |
| gpt-oss-20b | Not in LiveBench 2026-06-25 | 1,317 | ~22 GBTight fit | 11.6 | Apache 2.0 | 5.6M |
| Devstral Small 2 24B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~24 GBTight fit | 14.3 | Apache 2.0 | 24.8K |
With 32 GB you also run… 47
The next memory size on this ladder runs these well. Figures are the requirement on this hardware type.
- Gemma 4 26B A4BGoogle~25 GBQ4 · published params
- Mistral Small 3.2 24BMistral~25 GBQ4 · tensor count
- Qwen3.8 27BAlibaba~27 GBQ4 · published params
- Qwen3.6 27BAlibaba~27 GBQ4 · published params
- Smaug MiniAbacus AI~27 GBQ4 · published params
- Qwen3 Coder 30B A3BAlibaba~29 GBQ4 · published params
- GLM-4.7 FlashZ.ai~29 GBQ4 · published params
- Nemotron 3.5 Lightning 30B A3BNVIDIA~29 GBQ4 · published params
- Qwen3 30B A3B Instruct 2507Alibaba~29 GBQ4 · published params
- Granite 4.2 30BIBM~29 GBQ4 · published params
- Gemma 4 31BGoogle~30 GBQ4 · published params
- Olmo 3 32B ThinkAi2~30 GBQ4 · published params
- delphi-1e23-wc50m-warmup-levanter-sftlaion~25 GBQ4 · tensor count
- delphi-1e23-magpie-warmup-levanter-sftlaion~25 GBQ4 · tensor count
- gemma-2-27b-itgoogle~27 GBQ4 · tensor count
- gemma-2-27bgoogle~27 GBQ4 · tensor count
- txgemma-27b-chatgoogle~27 GBQ4 · tensor count
- shieldgemma-27bgoogle~27 GBQ4 · tensor count
- datagemma-rag-27b-itgoogle~27 GBQ4 · tensor count
- datagemma-rig-27b-itgoogle~27 GBQ4 · tensor count
- txgemma-27b-predictgoogle~27 GBQ4 · tensor count
- granite-4.1-30bibm-granite~28 GBQ4 · tensor count
- granite-4.1-30b-baseibm-granite~28 GBQ4 · tensor count
- Qwen3-30B-A3BQwen~29 GBQ4 · tensor count
- Qwen3-30B-A3B-Thinking-2507Qwen~29 GBQ4 · tensor count
- Qwen3-30B-A3B-BaseQwen~29 GBQ4 · tensor count
- Tongyi-DeepResearch-30B-A3BAlibaba-NLP~29 GBQ4 · tensor count
- SciJudge-30BOpenMOSS-Team~29 GBQ4 · tensor count
- Rubicon-PreviewinclusionAI~29 GBQ4 · tensor count
- SciJudge-30B-2605OpenMOSS-Team~29 GBQ4 · tensor count
- SciThinker-30BOpenMOSS-Team~29 GBQ4 · tensor count
- browsesafeperplexity-ai~29 GBQ4 · tensor count
- tt-x15-megatron-51-30Blaion~29 GBQ4 · tensor count
- tt-x2_clip-hi0p2-60-30Blaion~29 GBQ4 · tensor count
- tt-x10-fsdp2-fa2-117-30Blaion~29 GBQ4 · tensor count
- tt-x2_clip-hi0p05-10-30Blaion~29 GBQ4 · tensor count
- tt-x4_temperature-t0p7-45-30Blaion~29 GBQ4 · tensor count
- tt-x1_lr-lr8e6-60-30Blaion~29 GBQ4 · tensor count
- tt-x16-entropy0p003-42-30Blaion~29 GBQ4 · tensor count
- tt-x2_clip-hi0p01-15-30Blaion~29 GBQ4 · tensor count
- tt-x1_lr-lr4e6-30-30Blaion~29 GBQ4 · tensor count
- tt-x4_temperature-t1p0-45-30Blaion~29 GBQ4 · tensor count
- tt-x0_verifier-shaped-20-30Blaion~29 GBQ4 · tensor count
- tt-x0_verifier-binary-20-30Blaion~29 GBQ4 · tensor count
- tt-x5_gradnorm-gn1p8laion~29 GBQ4 · tensor count
- tt-x5_gradnorm-gn0p9laion~29 GBQ4 · tensor count
- tt-x3_kl-kl0laion~29 GBQ4 · tensor count
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 | ~13 GB | Q4 · Hugging Face count |
|---|---|---|---|
| Qwen2-VL-7B-InstructQ4 · Hugging Face count · source | 1,031 ± 11 | ~13 GB | Q4 · Hugging Face count |
| Molmo-7B-D-0924Q4 · Hugging Face count · source | 994 ± 14 | ~13 GB | Q4 · Hugging Face count |
| Llama-3.2-11B-Vision-InstructQ4 · Hugging Face count · source | 993 ± 11 | ~15 GB | Q4 · Hugging Face count |
| MiniCPM-V-2_6Q4 · Hugging Face count · source | 962 ± 16 | ~13 GB | Q4 · Hugging Face count |
| Phi-3.5-vision-instructQ4 · Hugging Face count · source | 919 ± 16 | ~10 GB | Q4 · Hugging Face count |
| Gemma 4 12BQ4 · published params · source | Not on the LMArena vision leaderboard of 2026-10-19 | ~15 GB | Q4 · published params |
| Qwen3.5 9BQ4 · published params · source | Not on the LMArena vision leaderboard of 2026-10-19 | ~13 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 2.4 GB free beyond the 6 GB the system keeps (the memory figure already includes that reserve).
With 32 GB you also run… 60
The next memory size on this ladder runs these well. Figures are the requirement on this hardware type.
- Gemma 4 26B A4BGoogle~25 GBQ4 · published params
- Qwen3.6 27BAlibaba~27 GBQ4 · published params
- Qwen3.8 27BAlibaba~27 GBQ4 · published params
- Smaug MiniAbacus AI~27 GBQ4 · published params
- Gemma 4 31BGoogle~30 GBQ4 · published params
- Ariarhymes-ai~25 GBQ4 · Hugging Face count
- Aria-Base-64Krhymes-ai~25 GBQ4 · Hugging Face count
- Aria-Base-8Krhymes-ai~25 GBQ4 · Hugging Face count
- Aria-Chatrhymes-ai~25 GBQ4 · Hugging Face count
- Aria-sequential_mlprhymes-ai~25 GBQ4 · Hugging Face count
- diffusiongemma-26B-A4B-itgoogle~26 GBQ4 · Hugging Face count
- gemma-4-26B-A4Bgoogle~26 GBQ4 · Hugging Face count
- InternVL-Chat-V1-5OpenGVLab~26 GBQ4 · Hugging Face count
- InternVL2_5-26BOpenGVLab~26 GBQ4 · Hugging Face count
- InternVL2_5-26B-MPOOpenGVLab~26 GBQ4 · Hugging Face count
- InternVL2-26BOpenGVLab~26 GBQ4 · Hugging Face count
- Sa2VA-26BByteDance~26 GBQ4 · Hugging Face count
- AREX-2BAAI~27 GBQ4 · Hugging Face count
- deepseek-vl2deepseek-ai~27 GBQ4 · Hugging Face count
- Fara1.5-27Bmicrosoft~27 GBQ4 · Hugging Face count
- Flora-Captionernvidia~27 GBQ4 · Hugging Face count
- Flora-Rewardernvidia~27 GBQ4 · Hugging Face count
- gemma-3-27b-itgoogle~27 GBQ4 · Hugging Face count
- gemma-3-27b-ptgoogle~27 GBQ4 · Hugging Face count
- Holo4-27BHcompany~27 GBQ4 · Hugging Face count
- medgemma-27b-itgoogle~27 GBQ4 · Hugging Face count
- paligemma2-28b-mix-224google~27 GBQ4 · Hugging Face count
- paligemma2-28b-mix-448google~27 GBQ4 · Hugging Face count
- paligemma2-28b-pt-224google~27 GBQ4 · Hugging Face count
- paligemma2-28b-pt-448google~27 GBQ4 · Hugging Face count
- paligemma2-28b-pt-896google~27 GBQ4 · Hugging Face count
- Qwen-Image-BenchQwen~27 GBQ4 · Hugging Face count
- Qwen3.5-27BQwen~27 GBQ4 · Hugging Face count
- Smaug-Political-Uncensoredabacusai~27 GBQ4 · Hugging Face count
- Smaug-Uncensoredabacusai~27 GBQ4 · Hugging Face count
- translategemma-27b-itgoogle~27 GBQ4 · Hugging Face count
- UI-Mate-27Btencent~27 GBQ4 · Hugging Face count
- UI-Mate-democua-27Btencent~27 GBQ4 · Hugging Face count
- ZwZ2-27BinclusionAI~27 GBQ4 · Hugging Face count
- mmE5-mllama-11b-instructintfloat~28 GB16-bit est. · Hugging Face count
- ERNIE-4.5-VL-28B-A3B-Base-Paddlebaidu~29 GBQ4 · Hugging Face count
- ERNIE-4.5-VL-28B-A3B-Base-PTbaidu~29 GBQ4 · Hugging Face count
- ERNIE-4.5-VL-28B-A3B-Paddlebaidu~29 GBQ4 · Hugging Face count
- ERNIE-4.5-VL-28B-A3B-PTbaidu~29 GBQ4 · Hugging Face count
- ERNIE-4.5-VL-28B-A3B-Thinkingbaidu~29 GBQ4 · Hugging Face count
- Hy-Embodied-VLM-1.0tencent~29 GBQ4 · Hugging Face count
- gemma-4-31Bgoogle~30 GBQ4 · Hugging Face count
- Holo2-30B-A3BHcompany~30 GBQ4 · Hugging Face count
- InternVL3_5-30B-A3BOpenGVLab~30 GBQ4 · Hugging Face count
- InternVL3_5-30B-A3B-FlashOpenGVLab~30 GBQ4 · Hugging Face count
- InternVL3_5-30B-A3B-HFOpenGVLab~30 GBQ4 · Hugging Face count
- InternVL3_5-30B-A3B-InstructOpenGVLab~30 GBQ4 · Hugging Face count
- InternVL3_5-30B-A3B-MPOOpenGVLab~30 GBQ4 · Hugging Face count
- InternVL3_5-30B-A3B-PretrainedOpenGVLab~30 GBQ4 · Hugging Face count
- Ising-Calibration-1.5-31B-BF16nvidia~30 GBQ4 · Hugging Face count
- Keye-VL-2.0-30B-A3BKwai-Keye~30 GBQ4 · Hugging Face count
- Prompt-RefineHiDream-ai~30 GBQ4 · Hugging Face count
- Qwen3-VL-30B-A3B-InstructQwen~30 GBQ4 · Hugging Face count
- Qwen3-VL-30B-A3B-ThinkingQwen~30 GBQ4 · Hugging Face count
- UI-Venus-1.5-30B-A3BinclusionAI~30 GBQ4 · Hugging Face count
471 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 |
| ETCHR-FLUX.2-klein-9B16-bit est. · params · source | No comparable published result | Not reviewed for LMArena | ~24 GB | 16-bit est. · params |
| FLUX.2 [klein] 9B16-bit est. · params · source | No comparable published result | 1,070 ± 3 | ~24 GB | 16-bit est. · params |
| FLUX.2 [klein] Base 9B16-bit est. · params · source | No comparable published result | Arena rated flux-2-klein-9b; this entry is the undistilled Base checkpoint | ~24 GB | 16-bit est. · params |
| FLUX.2-klein-9b-kv16-bit est. · params · source | No comparable published result | Not reviewed for LMArena | ~24 GB | 16-bit est. · params |
| HiDream-O1-Image-Dev-260416-bit est. · params · source | No comparable published result | Not reviewed for LMArena | ~24 GB | 16-bit est. · params |
| ERNIE Image16-bit est. · params · source | No comparable published result | Not on the LMArena text-to-image leaderboard of 2026-10-07 | ~22 GB | 16-bit est. · params |
LMArena ratings in this table: LMArena 2026-10-07 · collected 2026-10-25 · dataset · CC BY 4.0
With 32 GB you also run… 15
The next memory size on this ladder. Figures are the requirement on this hardware type.
- Ideogram 4.0Ideogram~25 GB16-bit est. · params
- Ideogram 4.0 (Quality)Ideogram~25 GB16-bit est. · params
- Ideogram 4.0 FastFal~25 GB16-bit est. · params
- Ideogram 4.0 Fast (Quality)Fal~25 GB16-bit est. · params
- Ideogram 4.0 InstantFal~25 GB16-bit est. · params
- Qwen-Image-2.1-PE-T2IQwen~25 GB16-bit est. · params
- FLUX.1 Krea [dev]Black Forest Labs~31 GB16-bit est. · params
- FLUX.1-Canny-devblack-forest-labs~31 GB16-bit est. · params
- FLUX.1-Depth-devblack-forest-labs~31 GB16-bit est. · params
- FLUX.1-Kontext-devblack-forest-labs~31 GB16-bit est. · params
- SRPOTencent~31 GB16-bit est. · params
- Qwen-Image-NVFP4nvidia~32 GB16-bit est. · params
- Step1X-Edit-v1p1-diffusersstepfun-ai~32 GB16-bit est. · params
- Step1X-Edit-v1p2stepfun-ai~32 GB16-bit est. · params
- Step1X-Edit-v1p2-previewstepfun-ai~32 GB16-bit est. · params
231 more image models in the catalog have no usable memory figure or parameter count for this profile. Browse Image models
Video
| ContentV-8B16-bit est. · params · source | ~22 GB | 16-bit est. · params |
|---|---|---|
| HunyuanVideo-1.516-bit est. · params · source | ~22 GB | 16-bit est. · params |
| 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 |
| SkyReels-A116-bit est. · params · source | ~16 GB | 16-bit est. · params |
| CogVideoX-5B16-bit est. · params · source | ~14 GB | 16-bit est. · params |
| EdenLive-5B-Causal-Diffusers16-bit est. · params · source | ~14 GB | 16-bit est. · params |
How this list works Documented execution paths on this hardware first, then publisher minimums (CUDA or Apple MPS).
With 32 GB you also run… 3
The next memory size on this ladder. Figures are the requirement on this hardware type.
- mochi-1-previewgenmo~26 GB16-bit est. · params
- Open-Sora-v2hpcai-tech~29 GB16-bit est. · params
- Video-As-Prompt-CogVideoX-5BByteDance~29 GB16-bit est. · params
125 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 |
| higgs-audio-v3-8b-stt16-bit est. · params · source | No comparable published result | ~24 GB | 16-bit est. · params |
| higgs-audio-v3-8b-stt-v216-bit est. · params · source | No comparable published result | ~24 GB | 16-bit est. · params |
| Ming-3.0-asr-tiny16-bit est. · params · source | No comparable published result | ~24 GB | 16-bit est. · params |
| Ming-3.0-audio-tiny16-bit est. · params · source | No comparable published result | ~24 GB | 16-bit est. · params |
| Ming-3.0-tts-tiny16-bit est. · params · source | No comparable published result | ~24 GB | 16-bit est. · params |
| MOSS-Audio-8B-Instruct16-bit est. · params · source | No comparable published result | ~24 GB | 16-bit est. · params |
With 32 GB you also run… 8
The next memory size on this ladder. Figures are the requirement on this hardware type.
- Kimi-Audio-7Bmoonshotai~26 GB16-bit est. · params
- Kimi-Audio-7B-Instructmoonshotai~26 GB16-bit est. · params
- MERaLiON-3-10BMERaLiON~26 GB16-bit est. · params
- MERaLiON-AudioLLM-Whisper-SEA-LIONMERaLiON~26 GB16-bit est. · params
- MERaLiON-2-10BMERaLiON~27 GB16-bit est. · params
- MERaLiON-2-10B-ASRMERaLiON~27 GB16-bit est. · params
- acestep-captionerACE-Step~28 GB16-bit est. · params
- acestep-transcriberACE-Step~28 GB16-bit est. · params
1,986 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 |
Runs well within 24 GB of unified memory · planning estimates, not measured speed
Measurements
Speed on this hardware
We have not yet included a verifiable measurement for this exact configuration. The memory estimates above do not indicate tokens per second or time to first token.Specifications
21 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 32 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
- 24 GB
- Memory type
- 24 GB unified
- Chip / processor
- Apple M5 · 10-core CPU · 8- or 10-core GPU
- Memory bandwidth
- 153 GB/s
- CPU
- Apple M5
- CPU cores
- 10
Family specification
Latest check · Manufacturer source
- Introduced
- 2026
- Storage options (family)
- 512 GB · 1 TB · 2 TB · 4 TB SSD
- Ports
- 2 × Thunderbolt 4 · MagSafe 3 · 3.5 mm
- Battery capacity
- 53.8 Wh
- Wi-Fi
- Wi-Fi 7 (802.11be)
- Bluetooth
- Bluetooth 6
- Dimensions (cm)
- 30.41 × 21.5 × 1.13 (W × D × H)
- Display size
- 13.6 in
- Display resolution
- 2560 × 1664
- Neural Engine cores
- 16
- Maximum Thunderbolt rate
- 40 Gb/s
- Weight
- 1.23 kg
- Operating system
- macOS
Apple lists a configurable 24 GB option for the 13-inch M5 Air, with 153 GB/s memory bandwidth. GPU core count depends on the purchased configuration. Memory is shared with macOS and applications; runtime and speed remain unverified.
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; 6 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 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 Pro 14-inch · M5 Pro · 18-core CPU / 20-core GPU · 24 GB unified
- MacBook Pro 16-inch · M5 Pro · 18-core CPU / 20-core GPU · 24 GB unified
Less memory · 16 GB 8
- iMac 24-inch · M4 · 8-core CPU / 8-core GPU · 16 GB unified
- Mac mini M1 · 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 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
More memory · 32 GB 8
- Dell XPS 14 (2026, DA14260) · Core Ultra 7 358H · Intel Arc Graphics · 32 GB
- Mac mini M4 · 32 GB unified
- Mac mini M6 · 32 GB unified
- MacBook Air 13-inch M4 · 32 GB unified
- MacBook Air 15-inch · M5 · 10-core CPU / 10-core GPU · 32 GB unified
- MacBook Pro 14-inch (M5) · M5 · 10-core CPU / 10-core GPU · 32 GB unified
- ThinkPad T14 Gen 5 AMD · MTM 21MDS2H10D
- ThinkPad X1 Carbon Gen 14 Aura Edition · MTM 21V7006EUS
