VOOZH about

URL: https://willitrunai.com/my-results/m3-max-64gb

⇱ MacBook Pro M3 Max 64GB AI Tier List: 317 models ranked | WillItRunAI


AI Compatibility Tier List

MacBook Pro M3 Max 64GB

374 AI models ranked by how well they run on your 64 GB unified memory hardware. Best match: Qwen 3.6 35B A3B (score: 96).

374

Models tested

317

Can run

64 GB

unified memory

34

Best tok/s

Tier Distribution

S 21
A 58
B 46
C 192
F 57
S: 21A: 58B: 46C: 192F: 57
S

S Tier -- Perfect Fit (21 models)

These models run flawlessly with headroom to spare.

👁 Alibaba
Qwen 3.6 35B A3B
S96
35B33.3 GB34 tok/s66K ctx
+1moe
👁 Alibaba
Qwen3-Coder 30B A3B Instruct
S95
30.5B27.9 GB36 tok/s215K ctx
moe
👁 Alibaba
Qwen 3.5 35B A3B
S95
35B30.6 GB37 tok/s131K ctx
moe
👁 Alibaba
Qwen3-VL 30B A3B Instruct
S94
30B27.6 GB38 tok/s218K ctx
moe
👁 Alibaba
Qwen 3 30B A3B
S92
30.5B27.9 GB36 tok/s131K ctx
moe
👁 Alibaba
Qwen 3.5 27B
S92
27B27.5 GB16 tok/s110K ctx
dense
👁 Alibaba
Qwen 3 32B
S91
32B31.2 GB13 tok/s77K ctx
dense
👁 NVIDIA
Nemotron Cascade 2 30B A3B
S90
30B29.0 GB37 tok/s109K ctx
moe
👁 Mistral
Magistral Small 2507
S90
24B24.9 GB18 tok/s131K ctx
dense
👁 Alibaba
Qwen 3.6 27B
S90
27B25.3 GB12 tok/s262K ctx
+1dense
👁 Mistral
Devstral Small 2 24B Instruct
S89
24B24.9 GB18 tok/s155K ctx
dense
👁 NVIDIA
Nemotron 3 Nano 30B
S89
30B28.6 GB14 tok/s131K ctx
dense
👁 OpenAI
GPT-OSS 20B
S89
21B23.1 GB46 tok/s128K ctx
moe
👁 Alibaba
Qwen 3.5 9B
S89
9B15.5 GB47 tok/s131K ctx
dense
👁 Alibaba
Qwen 3 14B
S88
14B18.8 GB30 tok/s131K ctx
dense
👁 Mistral
Devstral Small 1.1
S88
24B24.9 GB18 tok/s131K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
S87
14.7B19.8 GB29 tok/s33K ctx
dense
👁 Alibaba
Qwen 3 8B
S87
8B14.9 GB53 tok/s131K ctx
dense
👁 Google
Gemma 4 26B A4B
S87
25.2B26.8 GB39 tok/s100K ctx
moe
👁 Alibaba
Qwen 3.5 4B
S86
4B12.4 GB56 tok/s131K ctx
dense
👁 LG AI
EXAONE 4.0 32B
S85
32B31.2 GB13 tok/s77K ctx
dense
A

A Tier -- Great Fit (58 models)

Excellent performance with comfortable memory margins.

👁 Alibaba
Qwen 2.5 32B
A84
32B31.2 GB13 tok/s77K ctx
dense
👁 Google
Gemma 4 31B
A84
30.7B41.2 GB10 tok/s21K ctx
dense
👁 Google
Gemma 3 27B
A83
27B35.5 GB12 tok/s31K ctx
dense
👁 Microsoft
Phi-4 Mini Reasoning 4B
A83
3.8B11.6 GB53 tok/s131K ctx
dense
👁 Allen AI
OLMo 2 32B
A83
32B31.2 GB13 tok/s4K ctx
dense
👁 IBM
Granite 4.1 30B
A82
30B30.0 GB14 tok/s82K ctx
dense
👁 Mistral
Mistral Small 3.2 24B
A82
24B24.9 GB18 tok/s131K ctx
vision
👁 Mistral
Ministral 3 14B
A82
14B18.8 GB30 tok/s195K ctx
multimodal
👁 NVIDIA
Nemotron Nano 8B
A82
8B14.6 GB53 tok/s131K ctx
dense
👁 Mistral
Codestral 2 25.08
A82
22B23.7 GB18 tok/s163K ctx
dense
A81
24B24.9 GB18 tok/s131K ctx
dense
A81
19B21.8 GB22 tok/s8K ctx
dense
👁 Mistral
Mistral Small 24B
A80
24B24.9 GB18 tok/s33K ctx
dense
👁 Mistral AI
Mistral Small 3.1 24B
A79
24B24.9 GB18 tok/s131K ctx
dense
👁 InternLM
InternVL2 8B
A79
8B14.6 GB53 tok/s8K ctx
dense
A79
14B19.4 GB30 tok/s16K ctx
dense
👁 DeepSeek
DeepSeek Coder V2 16B
A79
16B20.9 GB59 tok/s131K ctx
moe
👁 Moonshot AI
Kimi Linear 48B A3B
A79
48B38.0 GB8 tok/s155K ctx
linear
👁 Alibaba
Qwen 2.5 14B
A78
14B19.3 GB30 tok/s131K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 32B
A78
32B31.2 GB13 tok/s77K ctx
dense
👁 IBM
Granite Code 20B
A78
20B23.2 GB21 tok/s8K ctx
dense
👁 Mistral
Ministral 3 8B
A78
8B14.9 GB53 tok/s243K ctx
multimodal
👁 BigCode
StarCoder 15B
A78
15B33.3 GB23 tok/s8K ctx
dense
👁 Alibaba
Qwen 3 4B
A77
4B12.4 GB56 tok/s33K ctx
dense
👁 OpenBMB
MiniCPM-V 2.6 8B
A77
8B14.6 GB53 tok/s2K ctx
dense
👁 IBM
Granite Code 34B
A77
34B32.2 GB13 tok/s8K ctx
dense
👁 Google
Gemma 3 12B
A77
12B20.0 GB26 tok/s101K ctx
dense
👁 Defog
SQLCoder 7B
A77
7B14.0 GB60 tok/s8K ctx
dense
👁 NVIDIA
Nemotron Nano 9B v2
A76
9B15.7 GB47 tok/s131K ctx
dense
👁 Cohere
Command R 35B
A76
35B31.6 GB12 tok/s111K ctx
dense
👁 Meta
CodeLlama 13B Instruct
A76
13B27.9 GB30 tok/s16K ctx
dense
👁 Alibaba
Qwen 2.5 VL 7B
A76
7B12.9 GB61 tok/s33K ctx
dense
👁 Jina AI
Jina Embeddings v3
A76
0.57B10.9 GB8 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 32B
A76
32B31.2 GB13 tok/s33K ctx
dense
👁 Magistral AI
Magistral 7B
A75
7B14.0 GB60 tok/s8K ctx
dense
👁 BAAI
BGE M3
A75
0.57B10.1 GB8 tok/s8K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
A75
13B27.9 GB30 tok/s4K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
A74
9B13.9 GB48 tok/s131K ctx
dense
👁 AllenAI
OLMo 2 13B
A74
13B18.2 GB33 tok/s33K ctx
dense
👁 Google
Gemma 4 E4B
A73
8B14.0 GB40 tok/s128K ctx
dense
👁 Meta
CodeLlama 7B Instruct
A73
7B19.9 GB56 tok/s16K ctx
dense
👁 BigCode
StarCoder 7B
A73
7B19.4 GB56 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 7B
A72
7B12.9 GB61 tok/s131K ctx
dense
👁 DevStral AI
DevStral 7B
A72
7B14.0 GB60 tok/s8K ctx
dense
👁 Nous Research
Nous Dolphin 13B
A72
13B29.4 GB26 tok/s16K ctx
dense
👁 IBM
Granite Code 8B
A72
8B14.6 GB53 tok/s8K ctx
dense
👁 Nous Research
Nous Hermes 1.0
A72
9B25.5 GB44 tok/s16K ctx
dense
👁 WizardLM
WizardLM 13B
A72
13B27.9 GB30 tok/s8K ctx
dense
👁 LMSYS
Vicuna 13B
A72
13B27.9 GB30 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 14B
A72
14B19.3 GB30 tok/s33K ctx
dense
👁 Mistral AI
Codestral Mamba 7B
A72
7B12.6 GB65 tok/s262K ctx
state-space
👁 Mixedbread AI
mxbai Embed Large
A71
0.34B10.0 GB5 tok/s1K ctx
dense
👁 IBM
Granite 4.1 8B
A71
8B15.1 GB53 tok/s131K ctx
dense
👁 Mistral AI
Pixtral 12B
A71
12B17.6 GB35 tok/s131K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
A71
0.34B10.0 GB5 tok/s1K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 3B
A71
3B11.8 GB42 tok/s131K ctx
dense
👁 InternLM
InternLM 7B
A70
7B19.9 GB56 tok/s8K ctx
dense
👁 InternLM
InternLM Chat 7B
A70
7B19.9 GB56 tok/s8K ctx
dense
B

B Tier -- Good Fit (46 models)

Solid performance, may need quantization or reduced context.

👁 Google
Gemma 2 27B
B70
27B35.5 GB12 tok/s8K ctx
dense
👁 Google
Gemma 4 E2B
B69
5.1B11.5 GB64 tok/s128K ctx
dense
👁 BAAI
BGE Large EN v1.5
B69
0.34B10.0 GB5 tok/s1K ctx
dense
B68
7B15.0 GB60 tok/s8K ctx
dense
👁 Meta
Llama 3.1 8B
B68
8B14.6 GB53 tok/s128K ctx
dense
👁 WizardLM
WizardMath 7B
B68
7B14.0 GB60 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
B68
7B14.0 GB60 tok/s4K ctx
dense
👁 Baichuan
Baichuan 13B
B68
13B29.4 GB26 tok/s8K ctx
dense
👁 Zhipu
GLM-4 9B
B68
9B13.9 GB48 tok/s128K ctx
dense
👁 LLaVA
LLaVA 1.5 7B
B67
7B19.9 GB56 tok/s4K ctx
dense
👁 Google
Gemma 3 4B
B67
4B12.3 GB56 tok/s128K ctx
dense
👁 TII
Falcon 40B Instruct
B67
40B38.4 GB9 tok/s8K ctx
dense
👁 Nomic AI
Nomic Embed Text v1.5
B67
0.14B8.6 GB2 tok/s8K ctx
dense
👁 Mistral
Ministral 3 3B
B67
3B10.4 GB42 tok/s262K ctx
multimodal
👁 Alibaba
Qwen 2.5 Coder 7B
B66
7B12.9 GB61 tok/s131K ctx
dense
👁 Cerebras
Cerebras-GPT 13B
B66
13B26.9 GB26 tok/s47K ctx
dense
👁 Microsoft
Phi 4 Mini 4B
B66
4B11.7 GB56 tok/s128K ctx
dense
👁 MosaicML
MPT-7B-Instruct
B66
7B19.9 GB56 tok/s8K ctx
dense
👁 Baichuan
Baichuan 7B
B66
7B19.9 GB56 tok/s8K ctx
dense
👁 Alibaba
Qwen 3.5 2B
B65
2B10.7 GB28 tok/s131K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
B65
3.8B16.0 GB53 tok/s98K ctx
dense
👁 Mistral
Mixtral 8x7B
B64
47B38.4 GB17 tok/s33K ctx
moe
👁 Alibaba
Qwen 2.5 3B
B64
3B11.8 GB42 tok/s131K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 7B
B64
7B12.9 GB61 tok/s33K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
B63
4B16.1 GB56 tok/s98K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 8B
B63
8B14.6 GB53 tok/s33K ctx
dense
7B14.0 GB60 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 34B
B63
34B32.2 GB13 tok/s4K ctx
dense
👁 TII
Falcon 7B Instruct
B62
7B12.2 GB62 tok/s8K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B62
1.7B10.6 GB24 tok/s33K ctx
dense
👁 Google
Gemma 2 9B
B62
9B18.4 GB35 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 14B
B62
14B19.3 GB30 tok/s131K ctx
dense
👁 IBM
Granite 4.1 3B
B61
3B10.9 GB42 tok/s131K ctx
dense
B61
0.02B8.1 GB2 tok/s0K ctx
dense
👁 Meta
Llama 3.2 11B Vision
B61
11B16.5 GB39 tok/s16K ctx
vision
👁 IBM
Granite Code 3B
B61
3B12.1 GB42 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 1.5B
B60
1.5B9.2 GB21 tok/s33K ctx
dense
👁 Mistral
Mistral Nemo 12B
B59
12B17.6 GB35 tok/s128K ctx
dense
👁 Mistral
Mistral 7B Instruct v0.3
B59
7B14.0 GB60 tok/s8K ctx
dense
👁 01.AI
Yi Coder 9B
B59
9B14.8 GB48 tok/s131K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
B58
14B19.4 GB30 tok/s128K ctx
dense
👁 Mistral AI
Codestral 22B
B58
22B23.7 GB19 tok/s33K ctx
dense
👁 MosaicML
MPT-30B-Instruct
B57
30B52.8 GB9 tok/s8K ctx
dense
👁 Meta
Llama 3.2 3B
B57
3B11.4 GB42 tok/s128K ctx
dense
👁 Mistral
Ministral 8B
B56
8B14.9 GB53 tok/s131K ctx
dense
👁 InternLM
InternLM 20B
B56
20B40.5 GB17 tok/s8K ctx
dense
C

C Tier -- Tight Fit (192 models)

Runs with offloading or significant compromises.

👁 Cohere
Aya Expanse 32B
C55
32B29.8 GB13 tok/s8K ctx
dense
C53
3B11.6 GB42 tok/s128K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
C52
1.5B9.2 GB21 tok/s33K ctx
dense
👁 01.AI
Yi 34B Chat
C52
34B32.2 GB13 tok/s77K ctx
dense
👁 IBM
Granite 3.1 8B
C52
8B14.6 GB61 tok/s128K ctx
state-space
👁 TinyLlama
TinyLlama 1.1B
C52
1.1B8.8 GB15 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 9B
C51
9B14.8 GB48 tok/s4K ctx
dense
👁 Stability AI
StableLM 2 12B
C51
12B28.7 GB26 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
C51
7B12.9 GB61 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
C51
35B33.3 GB11 tok/s66K ctx
dense
Qwen3.5 35B A3B
C50
35B33.3 GB11 tok/s66K ctx
dense
👁 LMSYS
Vicuna 7B
C50
7B19.9 GB56 tok/s4K ctx
dense
Hermes 4.3 36B
C50
36B34.0 GB11 tok/s62K ctx
dense
EXAONE 4.0 32B
C50
32B31.1 GB12 tok/s80K ctx
dense
aya expanse 32b heretic MPOA i1
C50
32B31.1 GB12 tok/s80K ctx
dense
Baichuan M2 32B Q4 K M
C50
32B31.1 GB12 tok/s80K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
C50
1.5B9.2 GB21 tok/s131K ctx
dense
baichuan inc Baichuan M2 32B
C50
32B31.1 GB12 tok/s80K ctx
dense
👁 Unsloth
Qwen3.5 27B
C49
27B27.4 GB15 tok/s110K ctx
dense
👁 OpenChat
OpenChat 7B
C49
7B14.0 GB60 tok/s8K ctx
dense
👁 Unsloth
gemma 3 27b it
C49
27B27.4 GB15 tok/s110K ctx
dense
gemma 3 27b it
C49
27B27.4 GB15 tok/s110K ctx
dense
👁 Cohere
Aya Expanse 8B
C48
8B14.6 GB53 tok/s8K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
C48
24B25.3 GB16 tok/s134K ctx
dense
👁 BigCode
StarCoder2 15B
C48
15B19.8 GB25 tok/s16K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C48
24B25.3 GB16 tok/s134K ctx
dense
Mistral Small 24B Instruct 2501
C48
24B25.3 GB16 tok/s134K ctx
dense
mistral small 3.1 24b instruct 2503 hf
C48
24B25.3 GB16 tok/s134K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
C48
24B25.3 GB16 tok/s134K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
C48
24B25.3 GB16 tok/s134K ctx
dense
👁 Google
Gemma 3 1B
C48
1B8.8 GB14 tok/s33K ctx
dense
👁 Teknium
OpenHermes 2.5 7B
C48
7B14.0 GB60 tok/s8K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C48
24B25.3 GB16 tok/s134K ctx
dense
👁 Google
Gemma 2 2B
C48
2B10.6 GB28 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek LLM 7B
C48
7B19.4 GB56 tok/s4K ctx
dense
Codestral 22B v0.1
C48
22B23.8 GB18 tok/s154K ctx
dense
Codestral 22B v0.1
C48
22B23.8 GB18 tok/s154K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
C48
7B14.0 GB60 tok/s33K ctx
dense
8B14.6 GB53 tok/s33K ctx
dense
Codestral 22B v0.1
C47
22B23.8 GB18 tok/s154K ctx
dense
👁 UC Berkeley
Starling LM 7B
C47
7B14.0 GB60 tok/s8K ctx
dense
Codestral 22B v0.1 IMat
C47
22B23.8 GB18 tok/s154K ctx
dense
Codestral 22B v0.1 i1
C47
22B23.8 GB18 tok/s154K ctx
dense
Codestral 21B Pruned i1
C47
21B23.1 GB19 tok/s166K ctx
dense
internlm2 5 20b chat
C47
20B22.4 GB20 tok/s178K ctx
dense
internlm2 limarp chat 20b
C47
20B22.4 GB20 tok/s178K ctx
dense
internlm2 math plus 20b i1
C47
20B22.4 GB20 tok/s178K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
C47
4B12.2 GB56 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 6B
C47
6B12.4 GB71 tok/s4K ctx
dense
Llama 2 7B Chat
C47
7B12.9 GB56 tok/s663K ctx
dense
falcon mamba 7b instruct Q4 K M
C47
7B12.9 GB65 tok/s663K ctx
dense
Codestral RAG 19B Pruned i1
C47
19B21.6 GB21 tok/s192K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C47
0.5B8.3 GB7 tok/s131K ctx
dense
Mistral 7B Instruct v0.2
C47
7B12.9 GB56 tok/s663K ctx
dense
👁 Unsloth
Qwen3.5 9B
C47
9B14.4 GB44 tok/s497K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
C47
14B18.0 GB28 tok/s290K ctx
dense
Yi 1.5 6B Chat
C47
6B12.2 GB66 tok/s788K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C47
9B14.4 GB44 tok/s497K ctx
dense
Meta Llama 3.1 8B Instruct
C47
8B13.6 GB49 tok/s570K ctx
dense
Mistral 7B Instruct v0.3
C47
7B12.9 GB56 tok/s663K ctx
dense
llava llama 3 8b v1 1
C46
8B13.6 GB49 tok/s570K ctx
dense
stablelm 2 zephyr 1 6b
C46
6B12.2 GB66 tok/s788K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
C46
8B13.6 GB49 tok/s570K ctx
dense
Phi 4 reasoning vision 15B
C46
15B18.7 GB26 tok/s265K ctx
dense
StarCoder2 15B
C46
15B18.7 GB26 tok/s265K ctx
dense
Qwen3.5 9B
C46
9B14.4 GB44 tok/s497K ctx
dense
Meta Llama 3 8B Instruct
C46
8B13.6 GB49 tok/s570K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
C46
8B13.6 GB49 tok/s570K ctx
dense
Mamba Codestral 7B v0.1
C46
7B12.9 GB65 tok/s663K ctx
dense
Dolphin3.0 Llama3.1 8B
C46
8B13.6 GB49 tok/s570K ctx
dense
Llama 3 8B Instruct 32k v0.1
C46
8B13.6 GB49 tok/s570K ctx
dense
Meta Llama 3.1 8B Instruct
C46
8B13.6 GB49 tok/s570K ctx
dense
vntl llama3 8b v2
C46
8B13.6 GB49 tok/s570K ctx
dense
gemma 3 12b it
C46
12B16.5 GB33 tok/s352K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C46
8B13.6 GB49 tok/s570K ctx
dense
NousResearch Hermes 4 14B
C46
14B18.0 GB28 tok/s290K ctx
dense
Yi 1.5 6B Chat
C46
6B12.2 GB66 tok/s788K ctx
dense
👁 Intel
Neural Chat 7B
C46
7B14.0 GB60 tok/s8K ctx
dense
Mistral 7B Instruct v0.3
C46
7B12.9 GB56 tok/s663K ctx
dense
stablelm 2 1 6b chat imatrix
C46
6B12.2 GB66 tok/s788K ctx
dense
Hermes 2 Pro Mistral 7B
C46
7B12.9 GB56 tok/s663K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C46
8B13.6 GB49 tok/s570K ctx
dense
zephyr 7B beta
C46
7B12.9 GB56 tok/s663K ctx
dense
Yi Coder 9B Chat
C46
9B14.4 GB44 tok/s497K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C46
8B13.6 GB49 tok/s570K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C46
7B12.9 GB56 tok/s663K ctx
dense
glm 4 9b chat 1m
C46
9B14.4 GB44 tok/s497K ctx
dense
starcoder2 15b instruct v0.1
C46
15B18.7 GB26 tok/s265K ctx
dense
Hermes 3 Llama 3.1 8B
C46
8B13.6 GB49 tok/s570K ctx
dense
starcoder2 15b i1
C46
15B18.7 GB26 tok/s265K ctx
dense
Falcon H1R 7B
C46
7B12.9 GB56 tok/s663K ctx
dense
starcoder2 15b instruct v0.1
C46
15B18.7 GB26 tok/s265K ctx
dense
zephyr 7B alpha
C46
7B12.9 GB56 tok/s663K ctx
dense
speechless zephyr code functionary 7b
C46
7B12.9 GB56 tok/s663K ctx
dense
Hermes 2 Pro Llama 3 8B
C46
8B13.6 GB49 tok/s570K ctx
dense
Dolphin3.0 Llama3.1 8B
C46
8B13.6 GB49 tok/s570K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C46
10.7B15.6 GB37 tok/s405K ctx
dense
granite 8b code instruct 4k
C46
8B13.6 GB49 tok/s570K ctx
dense
StarCoder2 7B
C46
7B12.9 GB56 tok/s663K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C46
10.7B15.6 GB37 tok/s405K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
C46
14B18.0 GB28 tok/s290K ctx
dense
dolphin 2.9.4 llama3.1 8b
C46
8B13.6 GB49 tok/s570K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
C46
48B42.7 GB8 tok/s26K ctx
dense
japanese stablelm instruct gamma 7B
C46
7B12.9 GB56 tok/s663K ctx
dense
Yi 1.5 9B Chat
C46
9B14.4 GB44 tok/s497K ctx
dense
HelpingAI 15B i1
C46
15B18.7 GB26 tok/s265K ctx
dense
internlm JanusCoder 14B
C46
14B18.0 GB28 tok/s290K ctx
dense
Falcon H1 7B Instruct
C46
7B12.9 GB56 tok/s663K ctx
dense
👁 Unsloth
Falcon H1R 7B
C46
7B12.9 GB56 tok/s663K ctx
dense
EXAONE 3.5 7.8B Instruct
C46
7.8B13.5 GB50 tok/s587K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
C46
14B18.0 GB28 tok/s290K ctx
dense
HelpingAI2 6B
C46
6B12.2 GB66 tok/s788K ctx
dense
openchat 3.6 8b 20240522 IMat
C46
8B13.6 GB49 tok/s570K ctx
dense
EXAONE 3.5 7.8B Instruct
C46
7.8B13.5 GB50 tok/s587K ctx
dense
aya expanse 8b
C46
8B13.6 GB49 tok/s570K ctx
dense
HelpingAI2 6B i1
C46
6B12.2 GB66 tok/s788K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C46
7.8B13.5 GB50 tok/s587K ctx
dense
dolphin v2 8b abliterated i1
C46
8B13.6 GB49 tok/s570K ctx
dense
exaone 3.0 7.8b it
C46
7.8B13.5 GB50 tok/s587K ctx
dense
stabilityai japanese stablelm base gamma 7b
C46
7B12.9 GB56 tok/s663K ctx
dense
baichuan2 7b chat
C46
7B12.9 GB56 tok/s663K ctx
dense
aya expanse 8b orthogonal heretic i1
C46
8B13.6 GB49 tok/s570K ctx
dense
DiscoPOP zephyr 7b gemma
C46
7B12.9 GB56 tok/s663K ctx
dense
starcoder2 7b
C46
7B12.9 GB56 tok/s663K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C46
7B12.9 GB56 tok/s663K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C46
7B12.9 GB56 tok/s663K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C46
7B12.9 GB56 tok/s663K ctx
dense
HelpingAI2.5 5B i1
C46
5B11.4 GB70 tok/s962K ctx
dense
internlm2 math plus 7b IMat
C46
7B12.9 GB56 tok/s663K ctx
dense
solar finalised finetuned Model 10.7B i1
C46
10.7B15.6 GB37 tok/s405K ctx
dense
Yi 9B Coder i1
C46
9B14.4 GB44 tok/s497K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C46
7B12.9 GB56 tok/s663K ctx
dense
internlm2 5 7b chat i1
C46
7B12.9 GB56 tok/s663K ctx
dense
aya expanse 8b orthogonal heretic
C46
8B13.6 GB49 tok/s570K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C46
7B12.9 GB56 tok/s663K ctx
dense
MD Judge v0 2 internlm2 7b i1
C46
7B12.9 GB56 tok/s663K ctx
dense
SOLAR 10.7B v1.0
C46
10.7B15.6 GB37 tok/s405K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C46
7B12.9 GB56 tok/s663K ctx
dense
jointpreferences mistral 7b sft helpful
C46
7B12.9 GB56 tok/s663K ctx
dense
HelpingAI2 9B
C46
9B14.4 GB44 tok/s497K ctx
dense
zephyr 7b dpo full i1
C46
7B12.9 GB56 tok/s663K ctx
dense
blossom v3 baichuan2 7b i1
C46
7B12.9 GB56 tok/s663K ctx
dense
blossom v1 baichuan 7b i1
C46
7B12.9 GB56 tok/s663K ctx
dense
internlm2 5 1 8b chat i1
C46
8B13.6 GB49 tok/s570K ctx
dense
HelpingAI2 9B i1
C46
9B14.4 GB44 tok/s497K ctx
dense
internlm3 8b instruct abliterated i1
C46
8B13.6 GB49 tok/s570K ctx
dense
HelpingAI 9B 200k i1
C46
9B14.4 GB44 tok/s497K ctx
dense
👁 BigCode
StarCoder2 7B
C46
7B12.6 GB61 tok/s16K ctx
dense
HelpingAI 9B i1
C46
9B14.4 GB44 tok/s497K ctx
dense
HelpingAI2.5 10B i1
C46
10B15.1 GB39 tok/s439K ctx
dense
Helply 10.2b chat i1
C46
10.2B15.2 GB39 tok/s429K ctx
dense
👁 Unsloth
Qwen3.5 4B
C46
4B10.7 GB56 tok/s1223K ctx
dense
gemma 3 4b it
C45
4B10.7 GB56 tok/s1223K ctx
dense
gemma 3 4b it
C45
4B10.7 GB56 tok/s1223K ctx
dense
👁 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
C44
3B10.3 GB42 tok/s1643K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C44
3B10.0 GB42 tok/s1658K ctx
dense
Llama 3.2 3B Instruct
C44
3B10.0 GB42 tok/s1658K ctx
dense
Ministral 3 3B Instruct 2512
C44
3B10.0 GB42 tok/s1658K ctx
dense
HELVETE 3B
C44
3B10.0 GB42 tok/s1658K ctx
dense
Hermes 3 Llama 3.2 3B
C44
3B10.0 GB42 tok/s1658K ctx
dense
stablelm zephyr 3b
C44
3B10.0 GB42 tok/s1658K ctx
dense
StarCoder2 3B
C44
3B10.0 GB42 tok/s1658K ctx
dense
AI21 Jamba Reasoning 3B
C44
3B10.0 GB42 tok/s1658K ctx
dense
stablelm 3b 4e1t
C44
3B10.0 GB42 tok/s1658K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C44
3B10.0 GB42 tok/s1658K ctx
dense
ai21labs AI21 Jamba2 3B
C44
3B10.0 GB42 tok/s1658K ctx
dense
HelpingAI 3B hindi i1
C43
3B10.0 GB42 tok/s1658K ctx
dense
AI21 Jamba2 3B
C43
3B10.0 GB42 tok/s1658K ctx
dense
HelpingAI 3B hindi
C43
3B10.0 GB42 tok/s1658K ctx
dense
AI21 Jamba2 3B i1
C43
3B10.0 GB42 tok/s1658K ctx
dense
gemma 2 2b it
C43
2B9.7 GB28 tok/s2500K ctx
dense
EXAONE 3.5 2.4B Instruct
C43
2.4B9.6 GB34 tok/s2094K ctx
dense
👁 Google
gemma 2b
C43
2B9.3 GB28 tok/s2529K ctx
dense
Gemmasutra Mini 2B v1
C43
2B9.3 GB28 tok/s2529K ctx
dense
👁 BigCode
StarCoder2 3B
C43
3B10.1 GB42 tok/s16K ctx
dense
gemma 2 2b it
C42
2B9.3 GB28 tok/s2529K ctx
dense
👁 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
C41
1.5B8.9 GB21 tok/s3400K ctx
dense
stablelm 2 zephyr 1.6b
C41
1.6B9.0 GB22 tok/s3182K ctx
dense
logos16v2 stablelm2 1.6b i1
C41
1.6B9.0 GB22 tok/s3182K ctx
dense
Yi Coder 1.5B
C41
1.5B8.9 GB21 tok/s3400K ctx
dense
👁 Unsloth
Falcon H1 1.5B Instruct
C41
1.5B8.9 GB21 tok/s3400K ctx
dense
TinyLlama 1.1B Chat v1.0
C40
1.1B8.6 GB15 tok/s4667K ctx
dense
EXAONE 4.0 1.2B
C40
1.2B8.7 GB17 tok/s4271K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
C40
0.5B8.3 GB7 tok/s131K ctx
dense
Llama 3.2 1B Instruct Q8 0
C40
1B8.7 GB14 tok/s5113K ctx
dense
TinyLlama 1.1B Chat v0.3
C40
1.1B8.6 GB15 tok/s4667K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
C40
1.1B8.6 GB15 tok/s4667K ctx
dense
F

F Tier -- Can't Run (57 models)

Too heavy for this hardware.

Llama 3.2 1B Instruct
D40
1B8.5 GB14 tok/s5142K ctx
dense
gemma 3 1b it
D40
1B8.5 GB14 tok/s5142K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
D40
1.1B8.6 GB15 tok/s4667K ctx
dense
Falcon3 1B Instruct abliterated
D39
1B8.5 GB14 tok/s5142K ctx
dense
👁 DeepSeek
DeepSeek LLM 67B
D39
67B54.5 GB5 tok/s4K ctx
dense
SmolVLM 500M Instruct
D38
0.5B8.3 GB7 tok/s6057K ctx
dense
embeddinggemma 300M
D36
0.3B8.2 GB4 tok/s6084K ctx
dense
granite embedding 107m multilingual
D34
0.11B8.0 GB2 tok/s6112K ctx
dense
Falcon H1 Tiny 90M Instruct
D34
0.09B8.0 GB2 tok/s6114K ctx
dense
👁 Meta
Llama 3.1 70B
F0
70B55.4 GB5 tok/s4K ctx
dense
👁 Meta
Llama 3.3 70B
F0
70B55.4 GB5 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 72B
F0
72B56.6 GB4 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
F0
235B154.0 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder-Next
F0
80B58.1 GB13 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B303.5 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 122B A10B
F0
122B84.7 GB7 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B252.9 GB2 tok/s4K ctx
moe
👁 Mistral
Mixtral 8x22B
F0
141B97.2 GB3 tok/s4K ctx
moe
👁 Mistral
Devstral 2 123B Instruct
F0
123B88.2 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 4 119B
F0
119B85.8 GB8 tok/s4K ctx
moe
👁 Mistral
Leanstral 119B A6B
F0
119B89.2 GB7 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B424.9 GB2 tok/s4K ctx
+1moe
F0
744B480.7 GB2 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B486.8 GB2 tok/s4K ctx
moe
F0
1000B625.3 GB2 tok/s4K ctx
moe
F0
1000B625.3 GB2 tok/s4K ctx
+1moe
👁 DeepSeek
DeepSeek V3 671B
F0
671B476.7 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B476.7 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B871.7 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Flash
F0
284B167.1 GB4 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B476.7 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B210.4 GB3 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B210.4 GB3 tok/s4K ctx
moe
👁 Meta
Llama 4 Scout 17B 16E
F0
109B77.2 GB5 tok/s4K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B254.7 GB2 tok/s4K ctx
moe
👁 Cohere
Command R+ 104B
F0
104B74.7 GB2 tok/s4K ctx
dense
👁 Cohere
Command A 111B
F0
111B79.4 GB2 tok/s4K ctx
dense
👁 Mistral AI
Pixtral Large 124B
F0
124B88.8 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 VL 72B
F0
72B56.6 GB4 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
F0
72B56.6 GB4 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 70B
F0
70B55.4 GB5 tok/s4K ctx
dense
👁 Meta
Llama 3.1 405B
F0
405B262.6 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
F0
70B55.4 GB5 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 120B
F0
117B84.1 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B417.6 GB2 tok/s4K ctx
moe
MiniMax M2.7
F0
230B151.9 GB4 tok/s4K ctx
moe
Solar Open 100B
F0
100B80.5 GB2 tok/s4K ctx
dense
K EXAONE 236B A23B
F0
236B179.4 GB2 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F0
70B58.7 GB4 tok/s4K ctx
dense
Baichuan M3 235B
F0
235B178.7 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0
235B178.7 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F0
72B60.2 GB4 tok/s4K ctx
dense
Solar Open 100B i1
F0
100B80.5 GB2 tok/s4K ctx
dense
Solar Open 69B REAP i1
F0
69B58.0 GB4 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F0
70B58.7 GB4 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
F0
122B81.9 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 397B A17B
F0
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

View tier list

Mac Studio M2 Ultra 64GB

64 GB unified memory

View tier list

MacBook Pro M4 Max 64GB

64 GB unified memory

View tier list

MacBook Pro M4 Pro 64GB

64 GB unified memory

View tier list
Full MacBook Pro M3 Max 64GB pageCompare this hardware