Mac Studio M2 Ultra 64GB

35B33.3 GB22 tok/s66K ctx

👁 DeepSeek
DeepSeek R1 1.5B

C52

1.5B9.2 GB21 tok/s33K ctx

dense

👁 Alibaba
Qwen 2.5 Math 7B

C52

7B12.9 GB98 tok/s4K ctx

dense

Hermes 4.3 36B

36B34.0 GB21 tok/s62K ctx

👁 TinyLlama
TinyLlama 1.1B

C52

1.1B8.8 GB15 tok/s4K ctx

dense

EXAONE 4.0 32B

aya expanse 32b heretic MPOA i1

👁 LMSYS
Vicuna 7B

C52

7B19.9 GB98 tok/s4K ctx

dense

Baichuan M2 32B Q4 K M

baichuan inc Baichuan M2 32B

27B27.4 GB28 tok/s110K ctx

👁 Unsloth
Qwen3.5 27B

C51

27B27.4 GB28 tok/s110K ctx

dense

👁 Unsloth
gemma 3 27b it

C51

27B27.4 GB28 tok/s110K ctx

dense

gemma 3 27b it

C51

cognitivecomputations Dolphin Mistral 24B Venice Edition

👁 OpenChat
OpenChat 7B

C50

7B14.0 GB98 tok/s8K ctx

dense

👁 BigCode
StarCoder2 15B

C50

15B19.8 GB48 tok/s16K ctx

dense

👁 Unsloth
Mistral Small 3.2 24B Instruct 2506

C50

24B25.3 GB32 tok/s134K ctx

dense

Mistral Small 24B Instruct 2501

mistral small 3.1 24b instruct 2503 hf

👁 Cohere
Aya Expanse 8B

C50

8B14.6 GB102 tok/s8K ctx

dense

cognitivecomputations Dolphin3.0 R1 Mistral 24B

Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1

cognitivecomputations Dolphin Mistral 24B Venice Edition

Codestral 22B v0.1

Codestral 22B v0.1

👁 Alibaba
Qwen 2.5 1.5B

C50

1.5B9.2 GB21 tok/s131K ctx

dense

Codestral 22B v0.1

Codestral 22B v0.1 IMat

👁 Cognitive Computations
Dolphin 2.9 8B

C49

8B14.6 GB102 tok/s33K ctx

dense

Codestral 22B v0.1 i1

👁 DeepSeek
DeepSeek LLM 7B

C49

7B19.4 GB98 tok/s4K ctx

dense

👁 Teknium
OpenHermes 2.5 7B

C49

7B14.0 GB98 tok/s8K ctx

dense

Codestral 21B Pruned i1

21B23.1 GB36 tok/s166K ctx

internlm2 5 20b chat

20B22.4 GB38 tok/s178K ctx

internlm2 limarp chat 20b

20B22.4 GB38 tok/s178K ctx

internlm2 math plus 20b i1

20B22.4 GB38 tok/s178K ctx

Codestral RAG 19B Pruned i1

👁 Hugging Face H4
Zephyr 7B Beta

C49

7B14.0 GB98 tok/s33K ctx

dense

👁 Unsloth
Qwen3.5 9B

C49

9B14.4 GB85 tok/s497K ctx

dense

19B21.6 GB40 tok/s192K ctx

Qwen3.5 9B Uncensored HauhauCS Aggressive

Phi 4 reasoning vision 15B

👁 Unsloth
DeepSeek R1 Distill Qwen 14B

C49

14B18.0 GB54 tok/s290K ctx

dense

👁 UC Berkeley
Starling LM 7B

C49

7B14.0 GB98 tok/s8K ctx

dense

Qwen3.5 9B

StarCoder2 15B

Meta Llama 3.1 8B Instruct

llava llama 3 8b v1 1

gemma 3 12b it

12B16.5 GB63 tok/s352K ctx

NousResearch Hermes 4 14B

👁 Unsloth
DeepSeek R1 0528 Qwen3 8B

C48

8B13.6 GB95 tok/s570K ctx

dense

Meta Llama 3 8B Instruct

👁 Unsloth
DeepSeek R1 Distill Llama 8B

C48

8B13.6 GB95 tok/s570K ctx

dense

Yi Coder 9B Chat

Dolphin3.0 Llama3.1 8B

Llama 3 8B Instruct 32k v0.1

glm 4 9b chat 1m

Meta Llama 3.1 8B Instruct

vntl llama3 8b v2

starcoder2 15b instruct v0.1

DeepSeek R1 0528 Qwen3 8B

starcoder2 15b i1

starcoder2 15b instruct v0.1

DeepSeek R1 0528 Qwen3 8B

SOLAR 10.7B Instruct v1.0 uncensored

Nous Hermes 2 SOLAR 10.7B

Qwen3 8B DeepSeek v3.2 Speciale Distill

Yi 1.5 9B Chat

GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV

Hermes 3 Llama 3.1 8B

HelpingAI 15B i1

Llama 2 7B Chat

internlm JanusCoder 14B

GGUF SOLARized GraniStral 14B 1902 YeAM HCT

Mistral 7B Instruct v0.2

Hermes 2 Pro Llama 3 8B

Dolphin3.0 Llama3.1 8B

granite 8b code instruct 4k

Mistral 7B Instruct v0.3

dolphin 2.9.4 llama3.1 8b

Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored

48B42.7 GB16 tok/s26K ctx

openchat 3.6 8b 20240522 IMat

aya expanse 8b

Yi 9B Coder i1

solar finalised finetuned Model 10.7B i1

dolphin v2 8b abliterated i1

EXAONE 3.5 7.8B Instruct

👁 Google
Gemma 3 1B

C48

1B8.8 GB14 tok/s33K ctx

dense

SOLAR 10.7B v1.0

EXAONE 3.5 7.8B Instruct

HelpingAI2 9B

aya expanse 8b orthogonal heretic i1

EXAONE 3.5 7.8B Instruct i1

Mistral 7B Instruct v0.3

Hermes 2 Pro Mistral 7B

exaone 3.0 7.8b it

HelpingAI2 9B i1

HelpingAI 9B 200k i1

zephyr 7B beta

aya expanse 8b orthogonal heretic

Nous Hermes 2 Mistral 7B DPO

HelpingAI 9B i1

HelpingAI2.5 10B i1

10B15.1 GB76 tok/s439K ctx

Falcon H1R 7B

Helply 10.2b chat i1

10.2B15.2 GB75 tok/s429K ctx

falcon mamba 7b instruct Q4 K M

internlm2 5 1 8b chat i1

zephyr 7B alpha

speechless zephyr code functionary 7b

internlm3 8b instruct abliterated i1

👁 Google
Gemma 2 2B

C48

2B10.6 GB28 tok/s8K ctx

dense

StarCoder2 7B

japanese stablelm instruct gamma 7B

👁 Intel
Neural Chat 7B

C48

7B14.0 GB98 tok/s8K ctx

dense

Falcon H1 7B Instruct

👁 Unsloth
Falcon H1R 7B

C48

7B12.9 GB98 tok/s663K ctx

dense

Mamba Codestral 7B v0.1

stabilityai japanese stablelm base gamma 7b

baichuan2 7b chat

DiscoPOP zephyr 7b gemma

starcoder2 7b

zephyr 7b beta Mistral 7B Instruct v0.2

OpenChat 3.5 7B Qwen v2.0 i1

OpenChat 3.5 7B Starling v2.0 i1

internlm2 math plus 7b IMat

CodeNinja 1.0 OpenChat 7B i1

internlm2 5 7b chat i1

OpenSafetyLab MD Judge v0 2 internlm2 7b

MD Judge v0 2 internlm2 7b i1

Yi 1.5 6B Chat

zephyr 7b gemma sft african ultrachat 100k

jointpreferences mistral 7b sft helpful

zephyr 7b dpo full i1

blossom v3 baichuan2 7b i1

blossom v1 baichuan 7b i1

stablelm 2 zephyr 1 6b

👁 01.AI
Yi 1.5 6B

C47

6B12.4 GB84 tok/s4K ctx

dense

Yi 1.5 6B Chat

stablelm 2 1 6b chat imatrix

👁 BigCode
StarCoder2 7B

C47

7B12.6 GB98 tok/s16K ctx

dense

HelpingAI2 6B

HelpingAI2 6B i1

5B11.4 GB70 tok/s962K ctx

👁 NVIDIA
Nemotron Mini 4B

C47

4B12.2 GB56 tok/s4K ctx

dense

👁 Alibaba
Qwen 2.5 Coder 0.5B

C47

0.5B8.3 GB7 tok/s131K ctx

dense

HelpingAI2.5 5B i1

C46

4B10.7 GB56 tok/s1223K ctx

👁 Unsloth
Qwen3.5 4B

C46

4B10.7 GB56 tok/s1223K ctx

dense

gemma 3 4b it

C45

4B10.7 GB56 tok/s1223K ctx

gemma 3 4b it

C45

👁 Alibaba
Qwen 3 0.6B

C45

0.6B9.0 GB8 tok/s33K ctx

dense

👁 Meta
Llama 3.2 1B

C45

1B8.9 GB14 tok/s128K ctx

dense

Llama 3.2 3B Instruct

3B10.3 GB42 tok/s1643K ctx

👁 Qwen
Qwen2.5 3B Instruct

C44

3B10.0 GB42 tok/s1658K ctx

dense

Llama 3.2 3B Instruct

Ministral 3 3B Instruct 2512

HELVETE 3B

Hermes 3 Llama 3.2 3B

stablelm zephyr 3b

StarCoder2 3B

AI21 Jamba Reasoning 3B

stablelm 3b 4e1t

ai21labs AI21 Jamba Reasoning 3B

ai21labs AI21 Jamba2 3B

HelpingAI 3B hindi i1

AI21 Jamba2 3B

HelpingAI 3B hindi

AI21 Jamba2 3B i1

gemma 2 2b it

2B9.7 GB28 tok/s2500K ctx

EXAONE 3.5 2.4B Instruct

2.4B9.6 GB34 tok/s2094K ctx

👁 Google
gemma 2b

C43

2B9.3 GB28 tok/s2529K ctx

dense

Gemmasutra Mini 2B v1

2B9.3 GB28 tok/s2529K ctx

2B9.3 GB28 tok/s2529K ctx

👁 BigCode
StarCoder2 3B

C43

3B10.1 GB42 tok/s16K ctx

dense

gemma 2 2b it

C42

👁 Alibaba
Qwen 3.5 0.6B

C42

0.6B9.0 GB8 tok/s131K ctx

dense

👁 Qwen
Qwen2.5 1.5B Instruct

C42

1.5B8.9 GB21 tok/s3400K ctx

dense

👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B

C41

1.5B8.9 GB21 tok/s3400K ctx

dense

Yi Coder 1.5B Chat

1.5B8.9 GB21 tok/s3400K ctx

stablelm 2 zephyr 1.6b

1.6B9.0 GB22 tok/s3182K ctx

logos16v2 stablelm2 1.6b i1

1.6B9.0 GB22 tok/s3182K ctx

Yi Coder 1.5B

1.5B8.9 GB21 tok/s3400K ctx

👁 Unsloth
Falcon H1 1.5B Instruct

C41

1.5B8.9 GB21 tok/s3400K ctx

dense

👁 DeepSeek
DeepSeek LLM 67B

C41

67B54.5 GB10 tok/s4K ctx

dense

TinyLlama 1.1B Chat v1.0

1.1B8.6 GB15 tok/s4667K ctx

EXAONE 4.0 1.2B

1.2B8.7 GB17 tok/s4271K ctx

Llama 3.2 1B Instruct Q8 0

👁 Alibaba
Qwen 2.5 0.5B

C40

0.5B8.3 GB7 tok/s131K ctx

dense

1B8.7 GB14 tok/s5113K ctx

TinyLlama 1.1B Chat v0.3

1.1B8.6 GB15 tok/s4667K ctx

1B8.5 GB14 tok/s5142K ctx

👁 TinyLlama
TinyLlama 1.1B Chat v0.6

C40

1.1B8.6 GB15 tok/s4667K ctx

dense

F Tier -- Can't Run (56 models)

Too heavy for this hardware.

Llama 3.2 1B Instruct

D40

1B8.5 GB14 tok/s5142K ctx

gemma 3 1b it

D40

TinyLlama 1.1B Chat v1.0 imatrix

D40

1.1B8.6 GB15 tok/s4667K ctx

Falcon3 1B Instruct abliterated

D39

1B8.5 GB14 tok/s5142K ctx

0.5B8.3 GB7 tok/s6057K ctx

SmolVLM 500M Instruct

D38

0.3B8.2 GB4 tok/s6084K ctx

embeddinggemma 300M

D36

granite embedding 107m multilingual

D34

0.11B8.0 GB2 tok/s6112K ctx

Falcon H1 Tiny 90M Instruct

D34

0.09B8.0 GB2 tok/s6114K ctx

230B151.9 GB8 tok/s4K ctx

👁 Meta
Llama 3.1 70B

70B55.4 GB9 tok/s4K ctx

dense

👁 Meta
Llama 3.3 70B

70B55.4 GB9 tok/s4K ctx

dense

👁 Alibaba
Qwen 2.5 72B

72B56.6 GB9 tok/s4K ctx

dense

👁 Alibaba
Qwen 3 235B A22B

235B154.0 GB4 tok/s4K ctx

moe

👁 Alibaba
Qwen3-Coder-Next

80B58.1 GB23 tok/s4K ctx

moe

👁 Alibaba
Qwen3-Coder 480B A35B Instruct

480B303.5 GB3 tok/s4K ctx

moe

👁 Alibaba
Qwen 3.5 122B A10B

122B84.7 GB14 tok/s4K ctx

moe

👁 Alibaba
Qwen 3.5 397B A17B

397B252.9 GB4 tok/s4K ctx

moe

👁 Mistral
Mixtral 8x22B

141B97.2 GB5 tok/s4K ctx

moe

👁 Mistral
Devstral 2 123B Instruct

123B88.2 GB3 tok/s4K ctx

dense

👁 Mistral
Mistral Small 4 119B

119B85.8 GB14 tok/s4K ctx

moe

👁 Mistral
Leanstral 119B A6B

119B89.2 GB13 tok/s4K ctx

moe

👁 Mistral
Mistral Large 3

675B424.9 GB3 tok/s4K ctx

+1moe

👁 Z.ai
GLM-5

744B480.7 GB2 tok/s4K ctx

moe

👁 Z.ai
GLM-5.1

754B486.8 GB2 tok/s4K ctx

moe

👁 Moonshot AI
Kimi K2.5

1000B625.3 GB2 tok/s4K ctx

moe

👁 Moonshot AI
Kimi K2.6

1000B625.3 GB2 tok/s4K ctx

+1moe

👁 DeepSeek
DeepSeek V3 671B

671B476.7 GB2 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V3.1 671B

671B476.7 GB2 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V4 Pro

1600B871.7 GB2 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V4 Flash

284B167.1 GB7 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek R1 671B

671B476.7 GB2 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek Coder V2 236B

236B210.4 GB6 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V2.5 236B

236B210.4 GB6 tok/s4K ctx

moe

👁 Meta
Llama 4 Scout 17B 16E

109B77.2 GB9 tok/s4K ctx

moe

👁 Meta
Llama 4 Maverick 17B 128E

400B254.7 GB4 tok/s4K ctx

moe

👁 Cohere
Command R+ 104B

104B74.7 GB4 tok/s4K ctx

dense

👁 Cohere
Command A 111B

111B79.4 GB4 tok/s4K ctx

dense

👁 Mistral AI
Pixtral Large 124B

124B88.8 GB3 tok/s4K ctx

dense

👁 Alibaba
Qwen 2.5 VL 72B

72B56.6 GB9 tok/s4K ctx

dense

👁 Alibaba
Qwen 2.5 Math 72B

72B56.6 GB9 tok/s4K ctx

dense

👁 NVIDIA
Nemotron 70B

70B55.4 GB9 tok/s4K ctx

dense

👁 Meta
Llama 3.1 405B

405B262.6 GB2 tok/s4K ctx

dense

👁 DeepSeek
DeepSeek R1 Distill 70B

70B55.4 GB9 tok/s4K ctx

dense

👁 OpenAI
GPT-OSS 120B

117B84.1 GB3 tok/s4K ctx

dense

👁 DeepSeek
DeepSeek V3.2

671B417.6 GB3 tok/s4K ctx

moe

MiniMax M2.7

moe

Solar Open 100B

100B80.5 GB4 tok/s4K ctx

236B179.4 GB2 tok/s4K ctx

K EXAONE 236B A23B

Llama 3.3 70B Instruct

70B58.7 GB8 tok/s4K ctx

235B178.7 GB2 tok/s4K ctx

Baichuan M3 235B

235B178.7 GB2 tok/s4K ctx

Baichuan M3 235B i1

BaichuanMed OCR 72B i1

72B60.2 GB7 tok/s4K ctx

Solar Open 100B i1

100B80.5 GB4 tok/s4K ctx

Solar Open 69B REAP i1

69B58.0 GB8 tok/s4K ctx

stabilityai japanese stablelm instruct beta 70b

70B58.7 GB8 tok/s4K ctx

👁 Unsloth
Qwen3.5 122B A10B

122B81.9 GB4 tok/s4K ctx

dense

👁 Unsloth
Qwen3.5 397B A17B

397B296.5 GB2 tok/s4K ctx

dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

MacBook Pro M1 Max 64GB

64 GB unified memory

MacBook Pro M3 Max 64GB

64 GB unified memory

MacBook Pro M4 Max 64GB

64 GB unified memory

MacBook Pro M4 Pro 64GB

64 GB unified memory