Hardware Match

Which model for Mac Studio 192 Go?

144 GB usable for the model (75% of unified memory). 98 open-weight models fit in memory.

The margin goes to context: count ~1 GB per 8k tokens for a 7B model. A small margin means a short context.

Model	Elo	Quantization	RAM required	Margin	Memory headroom	Run
Gemma 4 31BGoogle · 31B	1452	FP16	70 Go	+74 Go	comfortable	Hugging Face ↗
Gemma 4 26B-A4BGoogle · 26B	1438	FP16	59 Go	+85 Go	comfortable	Hugging Face ↗
Qwen3.8 27BAlibaba · 27B	1438	FP16	61 Go	+83 Go	comfortable	Hugging Face ↗
Mistral Medium 3.5Mistral AI · 128B	1426	Q4_K_M	82 Go	+62 Go	comfortable	Hugging Face ↗
GLM-4.5 AirZ.ai · 106B	1373	Q8_0	127 Go	+17 Go	tight	Hugging Face ↗
Gemma 3 27BGoogle · 27B	1365	Q4_K_MFP16 also fits · 61 Go	19 Go	+125 Go	comfortable	ollama run gemma3:27b
Nemotron 3 Super 120B-A12BNVIDIA · 120B	1360	Q8_0	143 Go	+1 Go	tight	Hugging Face ↗
Mistral Small 3.2Mistral AI · 24B	1356	Q4_K_MFP16 also fits · 55 Go	17 Go	+127 Go	comfortable	ollama run mistral-small3.2
gpt-oss-120bOpenAI · 117B	1352	MXFP4	73 Go	+71 Go	comfortable	ollama run gpt-oss:120b
Qwen3 32BAlibaba · 32.8B	1347	Q4_K_MFP16 also fits · 74 Go	23 Go	+121 Go	comfortable	ollama run qwen3:32b
Gemma 3 12BGoogle · 12B	1342	Q4_K_MFP16 also fits · 28 Go	9 Go	+135 Go	comfortable	ollama run gemma3:12b
QwQ 32BAlibaba · 32.8B	1336	Q4_K_MFP16 also fits · 74 Go	23 Go	+121 Go	comfortable	ollama run qwq
Llama 4 ScoutMeta · 109B	1322	Q4_K_MQ8_0 also fits · 130 Go	70 Go	+74 Go	comfortable	ollama run llama4:scout
Gemma 3n E4BGoogle · 4B	1318	Q4_K_MFP16 also fits · 11 Go	5 Go	+139 Go	comfortable	ollama run gemma3n:e4b
Llama 3.3 70BMeta · 70.6B	1318	Q4_K_MQ8_0 also fits · 85 Go	46 Go	+98 Go	comfortable	ollama run llama3.3:70b
gpt-oss-20bOpenAI · 21B	1317	MXFP4	17 Go	+127 Go	comfortable	ollama run gpt-oss:20b
Nemotron 3 Nano 30B-A3BNVIDIA · 30B	1314	FP16	68 Go	+76 Go	comfortable	Hugging Face ↗
Granite 4.1 8BIBM · 8B	1304	FP16	20 Go	+124 Go	comfortable	Hugging Face ↗
Gemma 3 4BGoogle · 4B	1303	Q4_K_MFP16 also fits · 11 Go	5 Go	+139 Go	comfortable	ollama run gemma3:4b
Qwen2.5 72BAlibaba · 72.7B	1303	Q4_K_MQ8_0 also fits · 88 Go	48 Go	+96 Go	comfortable	ollama run qwen2.5:72b
Llama 3.1 Nemotron 70BNVIDIA · 70.6B	1299	Q4_K_MQ8_0 also fits · 85 Go	46 Go	+98 Go	comfortable	ollama run nemotron:70b
Qwen2.5-Coder 32BAlibaba · 32.8B	1271	Q4_K_MFP16 also fits · 74 Go	23 Go	+121 Go	comfortable	ollama run qwen2.5-coder:32b
Aya Expanse 32BCohere · 32.3B	1267	Q4_K_MFP16 also fits · 73 Go	22 Go	+122 Go	comfortable	ollama run aya-expanse:32b
Command R+Cohere · 104B	1262	Q4_K_MQ8_0 also fits · 124 Go	67 Go	+77 Go	comfortable	ollama run command-r-plus
Phi-4Microsoft · 14.7B	1256	Q4_K_MFP16 also fits · 34 Go	11 Go	+133 Go	comfortable	ollama run phi4
Phi-4 ReasoningMicrosoft · 14.7B	1256	Q4_K_MFP16 also fits · 34 Go	11 Go	+133 Go	comfortable	ollama run phi4-reasoning
OLMo 2 32BAllen AI · 32B	1252	FP16	72 Go	+72 Go	comfortable	Hugging Face ↗
CodestralMistral AI · 22.2B	1240	Q4_K_MFP16 also fits · 51 Go	16 Go	+128 Go	comfortable	ollama run codestral
Ministral 8BMistral AI · 8.02B	1238	FP16	20 Go	+124 Go	comfortable	Hugging Face ↗
Llama 3.1 8BMeta · 8.03B	1211	Q4_K_MFP16 also fits · 20 Go	7 Go	+137 Go	comfortable	ollama run llama3.1:8b
Mixtral 8x7BMistral AI · 46.7B	1197	Q4_K_MFP16 also fits · 105 Go	31 Go	+113 Go	comfortable	ollama run mixtral:8x7b
Llama 3.2 3BMeta · 3.21B	1167	Q4_K_MFP16 also fits · 9 Go	4 Go	+140 Go	comfortable	ollama run llama3.2:3b
Llama 3.2 1BMeta · 1.24B	1111	Q4_K_MFP16 also fits · 5 Go	3 Go	+141 Go	comfortable	ollama run llama3.2:1b
Mistral 7BMistral AI · 7.25B	1110	Q4_K_MFP16 also fits · 18 Go	7 Go	+137 Go	comfortable	ollama run mistral:7b

Not yet ranked by the Arena

No Arena Elo linked: recent release, model absent from the Arena, or a match we have not made yet.

Model	Elo	Quantization	RAM required	Margin	Memory headroom	Run
Qwen3 0.6BAlibaba · 0.6B	—	Q4_K_MFP16 also fits · 3 Go	2 Go	+142 Go	comfortable	ollama run qwen3:0.6b
Gemma 3 1BGoogle · 1B	—	Q4_K_MFP16 also fits · 4 Go	3 Go	+141 Go	comfortable	ollama run gemma3:1b
Phi-4 MiniMicrosoft · 3.8B	—	Q4_K_MFP16 also fits · 10 Go	4 Go	+140 Go	comfortable	ollama run phi4-mini
Qwen3 4BAlibaba · 4.02B	—	Q4_K_MFP16 also fits · 11 Go	5 Go	+139 Go	comfortable	ollama run qwen3:4b
Gemma 4 E2BGoogle · 2B	—	FP16	6 Go	+138 Go	comfortable	Hugging Face ↗
CodeGemma 7BGoogle · 8.5B	—	Q4_K_MFP16 also fits · 21 Go	7 Go	+137 Go	comfortable	ollama run codegemma
Command R7BCohere · 8B	—	Q4_K_MFP16 also fits · 20 Go	7 Go	+137 Go	comfortable	ollama run command-r7b
DeepSeek-R1 Distill 8BDeepSeek · 8.03B	—	Q4_K_MFP16 also fits · 20 Go	7 Go	+137 Go	comfortable	ollama run deepseek-r1:8b
Granite 3.3 8BIBM · 8.1B	—	Q4_K_MFP16 also fits · 20 Go	7 Go	+137 Go	comfortable	ollama run granite3.3:8b
Hermes 3 8BNous Research · 8.03B	—	Q4_K_MFP16 also fits · 20 Go	7 Go	+137 Go	comfortable	ollama run hermes3:8b
MiniCPM5-2BOpenBMB · 2.5B	—	FP16	7 Go	+137 Go	comfortable	Hugging Face ↗
Qwen3 8BAlibaba · 8.2B	—	Q4_K_MFP16 also fits · 20 Go	7 Go	+137 Go	comfortable	ollama run qwen3:8b
Falcon 3 10BTII · 10.3B	—	Q4_K_MFP16 also fits · 25 Go	8 Go	+136 Go	comfortable	ollama run falcon3:10b
Granite 4.1 3BIBM · 3B	—	FP16	9 Go	+135 Go	comfortable	Hugging Face ↗
Ministral 3 3BMistral AI · 3B	—	FP16	9 Go	+135 Go	comfortable	Hugging Face ↗
SmolLM3 3BHugging Face · 3.1B	—	FP16	9 Go	+135 Go	comfortable	Hugging Face ↗
Mistral Nemo 12BMistral AI · 12.2B	—	Q4_K_MFP16 also fits · 29 Go	10 Go	+134 Go	comfortable	ollama run mistral-nemo
Gemma 4 E4BGoogle · 4B	—	FP16	11 Go	+133 Go	comfortable	Hugging Face ↗
Qwen3 14BAlibaba · 14.8B	—	Q4_K_MFP16 also fits · 35 Go	11 Go	+133 Go	comfortable	ollama run qwen3:14b
DeepSeek-Coder-V2 LiteDeepSeek · 15.7B	—	Q4_K_MFP16 also fits · 37 Go	12 Go	+132 Go	comfortable	ollama run deepseek-coder-v2:16b
StarCoder 2BigCode · 16B	—	Q4_K_MFP16 also fits · 37 Go	12 Go	+132 Go	comfortable	ollama run starcoder2:15b
Devstral SmallMistral AI · 24B	—	Q4_K_MFP16 also fits · 55 Go	17 Go	+127 Go	comfortable	ollama run devstral
Lucie 7BOpenLLM France · 6.7B	—	FP16	17 Go	+127 Go	comfortable	Hugging Face ↗
Magistral SmallMistral AI · 24B	—	Q4_K_MFP16 also fits · 55 Go	17 Go	+127 Go	comfortable	ollama run magistral
OLMo 3 7BAllen AI · 7B	—	FP16	17 Go	+127 Go	comfortable	Hugging Face ↗
Apertus 8BSwiss AI · 8B	—	FP16	20 Go	+124 Go	comfortable	Hugging Face ↗
Ministral 3 8BMistral AI · 8B	—	FP16	20 Go	+124 Go	comfortable	Hugging Face ↗
InternLM3 8BShanghai AI Lab · 8.8B	—	FP16	21 Go	+123 Go	comfortable	Hugging Face ↗
EuroLLM 9BUTTER Project · 9.15B	—	FP16	22 Go	+122 Go	comfortable	Hugging Face ↗
DeepSeek-R1 Distill 32BDeepSeek · 32.8B	—	Q4_K_MFP16 also fits · 74 Go	23 Go	+121 Go	comfortable	ollama run deepseek-r1:32b
Gemma 4 12BGoogle · 12B	—	FP16	28 Go	+116 Go	comfortable	Hugging Face ↗
Ministral 3 14BMistral AI · 14B	—	FP16	33 Go	+111 Go	comfortable	Hugging Face ↗
Qwen3.6 27BAlibaba · 27B	—	FP16	61 Go	+83 Go	comfortable	Hugging Face ↗
Qwen3.6 35B-A3BAlibaba · 35B	—	FP16	79 Go	+65 Go	comfortable	Hugging Face ↗
Mistral Small 4Mistral AI · 119B	—	Q8_0	142 Go	+2 Go	tight	Hugging Face ↗

Image, video, audio and 3D

These models do not generate text, so the text Arena does not rank them. Indicative order, not a quality ranking.

Model	Elo	Quantization	RAM required	Margin	Memory headroom	Run
Kokoro-82MHexgrad · 0.08B	—	FP16	2 Go	+142 Go	comfortable	Hugging Face ↗
ChatterboxResemble AI · 0.5B	—	FP16	3 Go	+141 Go	comfortable	Hugging Face ↗
Parakeet TDT 0.6B v3NVIDIA · 0.6B	—	FP16	3 Go	+141 Go	comfortable	Hugging Face ↗
TripoSRStability AI · 0.5B	—	FP16	3 Go	+141 Go	comfortable	Hugging Face ↗
Stable Fast 3DStability AI · 1B	—	FP16	4 Go	+140 Go	comfortable	Hugging Face ↗
TRELLISMicrosoft · 1.2B	—	FP16	5 Go	+139 Go	comfortable	Hugging Face ↗
Whisper large-v3OpenAI · 1.55B	—	FP16	5 Go	+139 Go	comfortable	Hugging Face ↗
Dia 1.6BNari Labs · 1.6B	—	FP16	6 Go	+138 Go	comfortable	Hugging Face ↗
Hunyuan3D 2.1Tencent · 3B	—	FP16	9 Go	+135 Go	comfortable	Hugging Face ↗
Orpheus 3BCanopy Labs · 3B	—	FP16	9 Go	+135 Go	comfortable	Hugging Face ↗
Voxtral Mini 3BMistral AI · 3B	—	FP16	9 Go	+135 Go	comfortable	Hugging Face ↗
YuE2-3Bm-a-p (Multimodal Art Projection) · 3B	—	FP16	9 Go	+135 Go	comfortable	Hugging Face ↗
FLUX.2 [klein] 4BBlack Forest Labs · 4B	—	FP16	11 Go	+133 Go	comfortable	Hugging Face ↗
TRELLIS.2Microsoft · 4B	—	FP16	11 Go	+133 Go	comfortable	Hugging Face ↗
CogVideoX 5BZhipu AI · 5B	—	FP16	13 Go	+131 Go	comfortable	Hugging Face ↗
Wan 2.2 5BAlibaba · 5B	—	FP16	13 Go	+131 Go	comfortable	Hugging Face ↗
Ming-Image 0.1 DesignAnt Group · 6B	—	FP16	15 Go	+129 Go	comfortable	Hugging Face ↗
Z-Image TurboAlibaba · 6B	—	FP16	15 Go	+129 Go	comfortable	Hugging Face ↗
HunyuanVideo 1.5Tencent · 8.3B	—	FP16	20 Go	+124 Go	comfortable	Hugging Face ↗
GLM-ImageZhipu AI · 9B	—	FP16	22 Go	+122 Go	comfortable	Hugging Face ↗
Mochi 1Genmo · 10B	—	FP16	24 Go	+120 Go	comfortable	Hugging Face ↗
FLUX.1 [dev]Black Forest Labs · 12B	—	FP16	28 Go	+116 Go	comfortable	Hugging Face ↗
HiDream-I1HiDream · 17B	—	FP16	39 Go	+105 Go	comfortable	Hugging Face ↗
Qwen-Image 2512Alibaba · 20B	—	FP16	46 Go	+98 Go	comfortable	Hugging Face ↗
LTX-2.3Lightricks · 22B	—	FP16	50 Go	+94 Go	comfortable	Hugging Face ↗
Voxtral Small 24BMistral AI · 24B	—	FP16	55 Go	+89 Go	comfortable	Hugging Face ↗
Wan 2.2 A14BAlibaba · 27B	—	FP16	61 Go	+83 Go	comfortable	Hugging Face ↗
FLUX.2 [dev]Black Forest Labs · 32B	—	FP16	72 Go	+72 Go	comfortable	Hugging Face ↗
HunyuanImage 3.0Tencent · 80B	—	Q8_0	96 Go	+48 Go	comfortable	Hugging Face ↗

An “ollama run” command without a suffix pulls the Q4_K_M build from the Ollama library: the row then shows that quantization and its memory, and flags whether FP16 or Q8_0 would also fit. Exception: a model published in a native format (MXFP4 for gpt-oss, FP8 for DeepSeek V4.1) exists in one build only, which is what the command loads. via Hugging Face or an explicit Ollama tag.

Share this verdict

One link, the same shortlist, the same reasons.

Share on LinkedIn

Refine with the Finder Other configurations