AI Compatibility Tier List
RTX 5000 Ada 32GB
374 AI models ranked by how well they run on your 32 GB VRAM hardware. Best match: Qwen3-Coder 30B A3B Instruct (score: 99).
374
Models tested
309
Can run
32 GB
VRAM
70
Best tok/s
Tier Distribution
S 24
A 60
B 39
C 186
F 65
S: 24A: 60B: 39C: 186F: 65
S
S Tier -- Perfect Fit (24 models)
These models run flawlessly with headroom to spare.
S99
30.5B24.2 GB70 tok/s102K ctx
moe
S98
30B23.9 GB72 tok/s105K ctx
moe
S97
30.5B24.2 GB70 tok/s102K ctx
moe
S96
27B23.7 GB30 tok/s58K ctx
dense
S95
35B29.6 GB59 tok/s26K ctx
+1moe
S94
24B21.2 GB34 tok/s87K ctx
dense
S94
27B21.5 GB23 tok/s187K ctx
+1dense
S94
35B26.9 GB64 tok/s72K ctx
moe
S94
24B21.2 GB34 tok/s87K ctx
dense
S94
30B25.3 GB71 tok/s52K ctx
moe
S93
21B19.4 GB89 tok/s99K ctx
moe
S93
30B24.8 GB27 tok/s63K ctx
dense
S92
24B21.2 GB34 tok/s87K ctx
dense
S91
9B11.8 GB90 tok/s131K ctx
dense
S91
25.2B23.1 GB75 tok/s55K ctx
moe
S91
14B15.1 GB58 tok/s127K ctx
dense
S91
32B27.5 GB26 tok/s34K ctx
dense
S91
14.7B16.1 GB55 tok/s33K ctx
dense
S89
8B11.2 GB102 tok/s131K ctx
dense
S87
24B21.2 GB34 tok/s87K ctx
vision
S86
22B20.0 GB33 tok/s95K ctx
dense
S86
4B8.7 GB56 tok/s131K ctx
dense
S86
24B21.2 GB34 tok/s87K ctx
dense
S86
14B15.1 GB58 tok/s127K ctx
multimodal
A
A Tier -- Great Fit (60 models)
Excellent performance with comfortable memory margins.
A85
24B21.2 GB34 tok/s33K ctx
dense
A85
32B27.5 GB26 tok/s34K ctx
dense
A85
19B18.1 GB43 tok/s8K ctx
dense
A84
8B10.9 GB102 tok/s131K ctx
dense
A84
24B21.2 GB34 tok/s87K ctx
dense
A83
32B27.5 GB26 tok/s34K ctx
dense
A83
14B15.7 GB58 tok/s16K ctx
dense
A83
3.8B7.9 GB53 tok/s131K ctx
dense
A82
30B26.3 GB27 tok/s39K ctx
dense
A82
32B27.5 GB26 tok/s4K ctx
dense
A82
16B17.2 GB112 tok/s88K ctx
moe
A82
20B19.5 GB41 tok/s8K ctx
dense
A82
27B31.8 GB22 tok/s16K ctx
dense
A82
14B15.6 GB58 tok/s106K ctx
dense
A81
8B10.9 GB102 tok/s8K ctx
dense
A81
13B24.2 GB58 tok/s16K ctx
dense
A81
12B16.3 GB50 tok/s67K ctx
dense
A80
8B11.2 GB102 tok/s168K ctx
multimodal
A80
8B10.9 GB102 tok/s2K ctx
dense
A79
9B12.0 GB90 tok/s131K ctx
dense
A79
13B24.2 GB58 tok/s4K ctx
dense
A78
7B10.3 GB98 tok/s8K ctx
dense
A78
7B9.2 GB98 tok/s33K ctx
dense
A78
4B8.7 GB56 tok/s33K ctx
dense
A78
32B27.5 GB26 tok/s34K ctx
dense
A77
13B14.5 GB63 tok/s33K ctx
dense
A77
9B21.8 GB84 tok/s16K ctx
dense
A77
7B10.3 GB98 tok/s8K ctx
dense
A77
15B29.5 GB44 tok/s8K ctx
dense
A77
9B10.2 GB92 tok/s131K ctx
dense
A76
34B28.5 GB24 tok/s8K ctx
dense
A76
7B16.2 GB98 tok/s16K ctx
dense
A76
13B24.2 GB58 tok/s8K ctx
dense
A76
13B24.2 GB58 tok/s4K ctx
dense
A76
0.57B7.2 GB8 tok/s8K ctx
dense
A76
35B27.9 GB24 tok/s43K ctx
dense
A76
7B15.7 GB98 tok/s8K ctx
dense
A76
8B10.3 GB77 tok/s128K ctx
dense
A76
13B25.7 GB50 tok/s16K ctx
dense
A75
14B15.6 GB58 tok/s33K ctx
dense
A75
32B27.5 GB26 tok/s33K ctx
dense
A74
0.57B6.4 GB8 tok/s8K ctx
dense
A74
8B10.9 GB102 tok/s8K ctx
dense
A74
7B9.2 GB98 tok/s131K ctx
dense
A74
7B10.3 GB98 tok/s8K ctx
dense
A74
12B13.9 GB68 tok/s131K ctx
dense
A74
30.7B37.5 GB11 tok/s10K ctx
dense
A74
8B11.4 GB102 tok/s131K ctx
dense
A73
7B16.2 GB98 tok/s8K ctx
dense
A73
7B16.2 GB98 tok/s8K ctx
dense
A73
7B8.9 GB98 tok/s262K ctx
state-space
A71
13B25.7 GB50 tok/s8K ctx
dense
A71
13B23.2 GB50 tok/s30K ctx
dense
A71
0.34B6.3 GB5 tok/s1K ctx
dense
A71
7B16.2 GB98 tok/s4K ctx
dense
A70
3B8.1 GB42 tok/s131K ctx
dense
A70
8B10.9 GB102 tok/s128K ctx
dense
A70
9B10.2 GB92 tok/s128K ctx
dense
A70
0.34B6.3 GB5 tok/s1K ctx
dense
A70
7B11.3 GB98 tok/s8K ctx
dense
B
B Tier -- Good Fit (39 models)
Solid performance, may need quantization or reduced context.
B69
7B10.3 GB98 tok/s4K ctx
dense
B69
7B10.3 GB98 tok/s4K ctx
dense
B69
48B34.3 GB10 tok/s4K ctx
linear
B69
5.1B7.7 GB71 tok/s128K ctx
dense
B69
27B31.8 GB22 tok/s8K ctx
dense
B69
7B16.2 GB98 tok/s8K ctx
dense
B69
7B16.2 GB98 tok/s8K ctx
dense
B68
0.34B6.3 GB5 tok/s1K ctx
dense
B68
7B9.2 GB98 tok/s131K ctx
dense
B67
4B8.6 GB56 tok/s128K ctx
dense
B66
3B6.7 GB42 tok/s262K ctx
multimodal
B66
4B8.0 GB56 tok/s128K ctx
dense
B66
0.14B4.9 GB2 tok/s8K ctx
dense
B66
8B10.9 GB102 tok/s33K ctx
dense
B65
3.8B12.3 GB53 tok/s70K ctx
dense
B65
9B14.7 GB67 tok/s8K ctx
dense
B65
14B15.6 GB58 tok/s106K ctx
dense
B65
7B9.2 GB98 tok/s33K ctx
dense
B65
2B7.0 GB28 tok/s131K ctx
dense
B65
7B10.3 GB98 tok/s4K ctx
dense
B64
4B12.4 GB56 tok/s70K ctx
dense
B64
11B12.8 GB74 tok/s16K ctx
vision
B64
7B8.5 GB98 tok/s8K ctx
dense
B64
3B8.1 GB42 tok/s131K ctx
dense
B63
12B13.9 GB68 tok/s128K ctx
dense
B62
22B20.0 GB35 tok/s33K ctx
dense
B62
34B28.5 GB24 tok/s4K ctx
dense
B62
14B15.7 GB58 tok/s102K ctx
dense
B62
1.7B6.8 GB24 tok/s33K ctx
dense
B61
9B11.1 GB91 tok/s131K ctx
dense
B61
3B7.2 GB42 tok/s131K ctx
dense
B61
3B8.4 GB42 tok/s8K ctx
dense
B61
7B10.3 GB98 tok/s8K ctx
dense
B60
0.02B4.4 GB2 tok/s0K ctx
dense
B60
1.5B5.4 GB21 tok/s33K ctx
dense
B59
8B11.2 GB102 tok/s131K ctx
dense
B58
32B26.1 GB26 tok/s8K ctx
dense
B58
40B34.7 GB11 tok/s4K ctx
dense
B57
3B7.6 GB42 tok/s128K ctx
dense
C
C Tier -- Tight Fit (186 models)
Runs with offloading or significant compromises.
C55
12B24.9 GB50 tok/s4K ctx
dense
C55
47B34.7 GB21 tok/s4K ctx
moe
C54
8B10.9 GB112 tok/s128K ctx
state-space
C54
9B11.1 GB91 tok/s4K ctx
dense
C53
27B23.7 GB28 tok/s58K ctx
dense
C53
27B23.7 GB28 tok/s58K ctx
dense
C53
7B16.2 GB98 tok/s4K ctx
dense
gemma 3 27b it
C5327B23.7 GB28 tok/s58K ctx
dense
C53
24B21.6 GB32 tok/s75K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C5324B21.6 GB32 tok/s75K ctx
dense
Mistral Small 24B Instruct 2501
C5324B21.6 GB32 tok/s75K ctx
dense
mistral small 3.1 24b instruct 2503 hf
C5324B21.6 GB32 tok/s75K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
C5324B21.6 GB32 tok/s75K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
C5324B21.6 GB32 tok/s75K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C5324B21.6 GB32 tok/s75K ctx
dense
C52
3B7.9 GB42 tok/s128K ctx
dense
C52
7B9.2 GB98 tok/s4K ctx
dense
Codestral 22B v0.1
C5222B20.1 GB34 tok/s90K ctx
dense
Codestral 22B v0.1
C5222B20.1 GB34 tok/s90K ctx
dense
Codestral 22B v0.1
C5222B20.1 GB34 tok/s90K ctx
dense
C52
15B16.1 GB48 tok/s16K ctx
dense
Codestral 22B v0.1 IMat
C5222B20.1 GB34 tok/s90K ctx
dense
Codestral 22B v0.1 i1
C5222B20.1 GB34 tok/s90K ctx
dense
C51
1.5B5.4 GB21 tok/s33K ctx
dense
Codestral 21B Pruned i1
C5121B19.4 GB36 tok/s98K ctx
dense
C51
1.1B5.1 GB15 tok/s4K ctx
dense
internlm2 5 20b chat
C5120B18.6 GB38 tok/s107K ctx
dense
C51
34B28.5 GB24 tok/s31K ctx
dense
internlm2 limarp chat 20b
C5120B18.6 GB38 tok/s107K ctx
dense
internlm2 math plus 20b i1
C5120B18.6 GB38 tok/s107K ctx
dense
C51
7B10.3 GB98 tok/s8K ctx
dense
C51
7B15.7 GB98 tok/s4K ctx
dense
C51
8B10.9 GB102 tok/s8K ctx
dense
Codestral RAG 19B Pruned i1
C5119B17.9 GB40 tok/s117K ctx
dense
Phi 4 reasoning vision 15B
C5015B15.0 GB50 tok/s171K ctx
dense
StarCoder2 15B
C5015B15.0 GB50 tok/s171K ctx
dense
C50
14B14.3 GB54 tok/s189K ctx
dense
C50
8B10.9 GB102 tok/s33K ctx
dense
starcoder2 15b instruct v0.1
C5015B15.0 GB50 tok/s171K ctx
dense
starcoder2 15b i1
C5015B15.0 GB50 tok/s171K ctx
dense
NousResearch Hermes 4 14B
C5014B14.3 GB54 tok/s189K ctx
dense
starcoder2 15b instruct v0.1
C5015B15.0 GB50 tok/s171K ctx
dense
C50
35B29.6 GB22 tok/s26K ctx
dense
C50
7B10.3 GB98 tok/s8K ctx
dense
HelpingAI 15B i1
C5015B15.0 GB50 tok/s171K ctx
dense
Qwen3.5 35B A3B
C4935B29.6 GB22 tok/s26K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
C4914B14.3 GB54 tok/s189K ctx
dense
internlm JanusCoder 14B
C4914B14.3 GB54 tok/s189K ctx
dense
gemma 3 12b it
C4912B12.8 GB63 tok/s234K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
C4914B14.3 GB54 tok/s189K ctx
dense
C49
7B10.3 GB98 tok/s33K ctx
dense
EXAONE 4.0 32B
C4932B27.4 GB24 tok/s36K ctx
dense
aya expanse 32b heretic MPOA i1
C4932B27.4 GB24 tok/s36K ctx
dense
Baichuan M2 32B Q4 K M
C4932B27.4 GB24 tok/s36K ctx
dense
baichuan inc Baichuan M2 32B
C4932B27.4 GB24 tok/s36K ctx
dense
C49
9B10.6 GB84 tok/s340K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C499B10.6 GB84 tok/s340K ctx
dense
C49
7B10.3 GB98 tok/s8K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C4910.7B11.9 GB71 tok/s273K ctx
dense
Hermes 4.3 36B
C4936B30.3 GB21 tok/s23K ctx
dense
Qwen3.5 9B
C499B10.6 GB84 tok/s340K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C4910.7B11.9 GB71 tok/s273K ctx
dense
C49
1.5B5.4 GB21 tok/s131K ctx
dense
Meta Llama 3.1 8B Instruct
C498B9.9 GB94 tok/s393K ctx
dense
llava llama 3 8b v1 1
C498B9.9 GB94 tok/s393K ctx
dense
Yi Coder 9B Chat
C499B10.6 GB84 tok/s340K ctx
dense
C49
8B9.9 GB94 tok/s393K ctx
dense
glm 4 9b chat 1m
C499B10.6 GB84 tok/s340K ctx
dense
Meta Llama 3 8B Instruct
C498B9.9 GB94 tok/s393K ctx
dense
C49
8B9.9 GB94 tok/s393K ctx
dense
Dolphin3.0 Llama3.1 8B
C498B9.9 GB94 tok/s393K ctx
dense
Llama 3 8B Instruct 32k v0.1
C498B9.9 GB94 tok/s393K ctx
dense
solar finalised finetuned Model 10.7B i1
C4910.7B11.9 GB71 tok/s273K ctx
dense
Meta Llama 3.1 8B Instruct
C498B9.9 GB94 tok/s393K ctx
dense
vntl llama3 8b v2
C498B9.9 GB94 tok/s393K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C498B9.9 GB94 tok/s393K ctx
dense
SOLAR 10.7B v1.0
C4910.7B11.9 GB71 tok/s273K ctx
dense
Yi 1.5 9B Chat
C499B10.6 GB84 tok/s340K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C498B9.9 GB94 tok/s393K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C498B9.9 GB94 tok/s393K ctx
dense
Hermes 3 Llama 3.1 8B
C498B9.9 GB94 tok/s393K ctx
dense
Hermes 2 Pro Llama 3 8B
C488B9.9 GB94 tok/s393K ctx
dense
Dolphin3.0 Llama3.1 8B
C488B9.9 GB94 tok/s393K ctx
dense
granite 8b code instruct 4k
C488B9.9 GB94 tok/s393K ctx
dense
dolphin 2.9.4 llama3.1 8b
C488B9.9 GB94 tok/s393K ctx
dense
HelpingAI2.5 10B i1
C4810B11.4 GB76 tok/s298K ctx
dense
Yi 9B Coder i1
C489B10.6 GB84 tok/s340K ctx
dense
Helply 10.2b chat i1
C4810.2B11.5 GB74 tok/s290K ctx
dense
Llama 2 7B Chat
C487B9.2 GB98 tok/s461K ctx
dense
openchat 3.6 8b 20240522 IMat
C488B9.9 GB94 tok/s393K ctx
dense
Mistral 7B Instruct v0.2
C487B9.2 GB98 tok/s461K ctx
dense
aya expanse 8b
C488B9.9 GB94 tok/s393K ctx
dense
HelpingAI2 9B
C489B10.6 GB84 tok/s340K ctx
dense
dolphin v2 8b abliterated i1
C488B9.9 GB94 tok/s393K ctx
dense
Mistral 7B Instruct v0.3
C487B9.2 GB98 tok/s461K ctx
dense
EXAONE 3.5 7.8B Instruct
C487.8B9.8 GB97 tok/s405K ctx
dense
HelpingAI2 9B i1
C489B10.6 GB84 tok/s340K ctx
dense
HelpingAI 9B 200k i1
C489B10.6 GB84 tok/s340K ctx
dense
aya expanse 8b orthogonal heretic i1
C488B9.9 GB94 tok/s393K ctx
dense
EXAONE 3.5 7.8B Instruct
C487.8B9.8 GB97 tok/s405K ctx
dense
HelpingAI 9B i1
C489B10.6 GB84 tok/s340K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C487.8B9.8 GB97 tok/s405K ctx
dense
exaone 3.0 7.8b it
C487.8B9.8 GB97 tok/s405K ctx
dense
aya expanse 8b orthogonal heretic
C488B9.9 GB94 tok/s393K ctx
dense
Mistral 7B Instruct v0.3
C487B9.2 GB98 tok/s461K ctx
dense
C48
7B10.3 GB98 tok/s8K ctx
dense
Hermes 2 Pro Mistral 7B
C487B9.2 GB98 tok/s461K ctx
dense
internlm2 5 1 8b chat i1
C488B9.9 GB94 tok/s393K ctx
dense
internlm3 8b instruct abliterated i1
C488B9.9 GB94 tok/s393K ctx
dense
zephyr 7B beta
C487B9.2 GB98 tok/s461K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C487B9.2 GB98 tok/s461K ctx
dense
Falcon H1R 7B
C487B9.2 GB98 tok/s461K ctx
dense
falcon mamba 7b instruct Q4 K M
C487B9.2 GB98 tok/s461K ctx
dense
zephyr 7B alpha
C487B9.2 GB98 tok/s461K ctx
dense
speechless zephyr code functionary 7b
C487B9.2 GB98 tok/s461K ctx
dense
StarCoder2 7B
C487B9.2 GB98 tok/s461K ctx
dense
japanese stablelm instruct gamma 7B
C487B9.2 GB98 tok/s461K ctx
dense
Falcon H1 7B Instruct
C487B9.2 GB98 tok/s461K ctx
dense
C48
7B9.2 GB98 tok/s461K ctx
dense
Mamba Codestral 7B v0.1
C487B9.2 GB98 tok/s461K ctx
dense
stabilityai japanese stablelm base gamma 7b
C487B9.2 GB98 tok/s461K ctx
dense
baichuan2 7b chat
C487B9.2 GB98 tok/s461K ctx
dense
DiscoPOP zephyr 7b gemma
C487B9.2 GB98 tok/s461K ctx
dense
starcoder2 7b
C487B9.2 GB98 tok/s461K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C487B9.2 GB98 tok/s461K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C487B9.2 GB98 tok/s461K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C487B9.2 GB98 tok/s461K ctx
dense
internlm2 math plus 7b IMat
C487B9.2 GB98 tok/s461K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C487B9.2 GB98 tok/s461K ctx
dense
internlm2 5 7b chat i1
C487B9.2 GB98 tok/s461K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C487B9.2 GB98 tok/s461K ctx
dense
MD Judge v0 2 internlm2 7b i1
C487B9.2 GB98 tok/s461K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C477B9.2 GB98 tok/s461K ctx
dense
jointpreferences mistral 7b sft helpful
C477B9.2 GB98 tok/s461K ctx
dense
zephyr 7b dpo full i1
C477B9.2 GB98 tok/s461K ctx
dense
blossom v3 baichuan2 7b i1
C477B9.2 GB98 tok/s461K ctx
dense
blossom v1 baichuan 7b i1
C477B9.2 GB98 tok/s461K ctx
dense
Yi 1.5 6B Chat
C476B8.5 GB84 tok/s552K ctx
dense
C47
2B6.9 GB28 tok/s8K ctx
dense
stablelm 2 zephyr 1 6b
C476B8.5 GB84 tok/s552K ctx
dense
C47
1B5.1 GB14 tok/s33K ctx
dense
C47
6B8.7 GB84 tok/s4K ctx
dense
Yi 1.5 6B Chat
C476B8.5 GB84 tok/s552K ctx
dense
stablelm 2 1 6b chat imatrix
C476B8.5 GB84 tok/s552K ctx
dense
C47
7B8.9 GB98 tok/s16K ctx
dense
HelpingAI2 6B
C476B8.5 GB84 tok/s552K ctx
dense
HelpingAI2 6B i1
C476B8.5 GB84 tok/s552K ctx
dense
C47
4B8.5 GB56 tok/s4K ctx
dense
C47
20B36.8 GB18 tok/s8K ctx
dense
C46
0.5B4.6 GB7 tok/s131K ctx
dense
HelpingAI2.5 5B i1
C465B7.7 GB70 tok/s679K ctx
dense
C45
4B7.0 GB56 tok/s869K ctx
dense
gemma 3 4b it
C454B7.0 GB56 tok/s869K ctx
dense
gemma 3 4b it
C454B7.0 GB56 tok/s869K ctx
dense
Llama 3.2 3B Instruct
C443B6.6 GB42 tok/s1171K ctx
dense
C44
0.6B5.3 GB8 tok/s33K ctx
dense
C44
1B5.2 GB14 tok/s128K ctx
dense
C44
3B6.3 GB42 tok/s1186K ctx
dense
Llama 3.2 3B Instruct
C443B6.3 GB42 tok/s1186K ctx
dense
Ministral 3 3B Instruct 2512
C443B6.3 GB42 tok/s1186K ctx
dense
HELVETE 3B
C433B6.3 GB42 tok/s1186K ctx
dense
Hermes 3 Llama 3.2 3B
C433B6.3 GB42 tok/s1186K ctx
dense
stablelm zephyr 3b
C433B6.3 GB42 tok/s1186K ctx
dense
StarCoder2 3B
C433B6.3 GB42 tok/s1186K ctx
dense
AI21 Jamba Reasoning 3B
C433B6.3 GB42 tok/s1186K ctx
dense
stablelm 3b 4e1t
C433B6.3 GB42 tok/s1186K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C433B6.3 GB42 tok/s1186K ctx
dense
ai21labs AI21 Jamba2 3B
C433B6.3 GB42 tok/s1186K ctx
dense
HelpingAI 3B hindi i1
C433B6.3 GB42 tok/s1186K ctx
dense
AI21 Jamba2 3B
C433B6.3 GB42 tok/s1186K ctx
dense
HelpingAI 3B hindi
C433B6.3 GB42 tok/s1186K ctx
dense
AI21 Jamba2 3B i1
C433B6.3 GB42 tok/s1186K ctx
dense
gemma 2 2b it
C422B6.0 GB28 tok/s1793K ctx
dense
EXAONE 3.5 2.4B Instruct
C422.4B5.8 GB34 tok/s1504K ctx
dense
C42
3B6.4 GB42 tok/s16K ctx
dense
C42
2B5.6 GB28 tok/s1821K ctx
dense
Gemmasutra Mini 2B v1
C422B5.6 GB28 tok/s1821K ctx
dense
gemma 2 2b it
C422B5.6 GB28 tok/s1821K ctx
dense
C42
0.6B5.3 GB8 tok/s131K ctx
dense
C41
1.5B5.2 GB21 tok/s2456K ctx
dense
C41
1.5B5.2 GB21 tok/s2456K ctx
dense
Yi Coder 1.5B Chat
C411.5B5.2 GB21 tok/s2456K ctx
dense
stablelm 2 zephyr 1.6b
C401.6B5.3 GB22 tok/s2298K ctx
dense
logos16v2 stablelm2 1.6b i1
C401.6B5.3 GB22 tok/s2298K ctx
dense
Yi Coder 1.5B
C401.5B5.2 GB21 tok/s2456K ctx
dense
C40
1.5B5.2 GB21 tok/s2456K ctx
dense
F
F Tier -- Can't Run (65 models)
Too heavy for this hardware.
TinyLlama 1.1B Chat v1.0
D401.1B4.9 GB15 tok/s3380K ctx
dense
EXAONE 4.0 1.2B
D401.2B5.0 GB17 tok/s3091K ctx
dense
Llama 3.2 1B Instruct Q8 0
D401B5.0 GB14 tok/s3697K ctx
dense
D39
0.5B4.6 GB7 tok/s131K ctx
dense
TinyLlama 1.1B Chat v0.3
D391.1B4.9 GB15 tok/s3380K ctx
dense
D39
1.1B4.9 GB15 tok/s3380K ctx
dense
Llama 3.2 1B Instruct
D391B4.8 GB14 tok/s3726K ctx
dense
gemma 3 1b it
D391B4.8 GB14 tok/s3726K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
D391.1B4.9 GB15 tok/s3380K ctx
dense
Falcon3 1B Instruct abliterated
D391B4.8 GB14 tok/s3726K ctx
dense
SmolVLM 500M Instruct
D370.5B4.6 GB7 tok/s4398K ctx
dense
embeddinggemma 300M
D350.3B4.4 GB4 tok/s4425K ctx
dense
granite embedding 107m multilingual
D330.11B4.3 GB2 tok/s4454K ctx
dense
Falcon H1 Tiny 90M Instruct
D330.09B4.3 GB2 tok/s4455K ctx
dense
F0
70B51.7 GB3 tok/s4K ctx
dense
F0
70B51.7 GB3 tok/s4K ctx
dense
F0
72B52.9 GB3 tok/s4K ctx
dense
F0
235B150.3 GB2 tok/s4K ctx
moe
F0
80B54.4 GB8 tok/s4K ctx
moe
F0
480B299.8 GB2 tok/s4K ctx
moe
F0
122B81.0 GB3 tok/s4K ctx
moe
F0
397B249.1 GB2 tok/s4K ctx
moe
F0
141B93.5 GB2 tok/s4K ctx
moe
F0
30B49.1 GB7 tok/s4K ctx
dense
F0
123B84.5 GB2 tok/s4K ctx
dense
F0
119B82.1 GB3 tok/s4K ctx
moe
F0
119B85.5 GB3 tok/s4K ctx
moe
F0
675B421.2 GB2 tok/s4K ctx
+1moe
F0
744B477.0 GB2 tok/s4K ctx
moe
F0
754B483.1 GB2 tok/s4K ctx
moe
F0
1000B621.5 GB2 tok/s4K ctx
moe
F0
1000B621.5 GB2 tok/s4K ctx
+1moe
F0
671B473.0 GB2 tok/s4K ctx
moe
F0
671B473.0 GB2 tok/s4K ctx
moe
F0
1600B868.0 GB2 tok/s4K ctx
moe
F0
284B163.4 GB2 tok/s4K ctx
moe
F0
671B473.0 GB2 tok/s4K ctx
moe
F0
236B206.7 GB2 tok/s4K ctx
moe
F0
236B206.7 GB2 tok/s4K ctx
moe
F0
67B50.8 GB4 tok/s4K ctx
dense
F0
109B73.5 GB3 tok/s4K ctx
moe
F0
400B251.0 GB2 tok/s4K ctx
moe
F0
104B71.0 GB2 tok/s4K ctx
dense
F0
111B75.7 GB2 tok/s4K ctx
dense
F0
124B85.1 GB2 tok/s4K ctx
dense
F0
72B52.9 GB3 tok/s4K ctx
dense
F0
72B52.9 GB3 tok/s4K ctx
dense
F0
70B51.7 GB3 tok/s4K ctx
dense
F0
405B258.8 GB2 tok/s4K ctx
dense
F0
70B51.7 GB3 tok/s4K ctx
dense
F0
117B80.4 GB2 tok/s4K ctx
dense
F0
671B413.9 GB2 tok/s4K ctx
moe
MiniMax M2.7
F0230B148.2 GB2 tok/s4K ctx
moe
Solar Open 100B
F0100B76.8 GB2 tok/s4K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
F048B39.0 GB8 tok/s4K ctx
dense
K EXAONE 236B A23B
F0236B175.7 GB2 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F070B55.0 GB3 tok/s4K ctx
dense
Baichuan M3 235B
F0235B175.0 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0235B175.0 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F072B56.5 GB2 tok/s4K ctx
dense
Solar Open 100B i1
F0100B76.8 GB2 tok/s4K ctx
dense
Solar Open 69B REAP i1
F069B54.3 GB3 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F070B55.0 GB3 tok/s4K ctx
dense
F0
122B78.2 GB2 tok/s4K ctx
dense
F0
397B292.8 GB2 tok/s4K ctx
dense
Compare with...
See How Other Hardware Stacks Up
Check tier lists for similar GPUs and Apple Silicon configs
