VOOZH about

URL: https://willitrunai.com/my-results/rtx-5070-ti-16gb

⇱ RTX 5070 Ti 16GB AI Tier List: 247 models ranked | WillItRunAI


AI Compatibility Tier List

RTX 5070 Ti 16GB

374 AI models ranked by how well they run on your 16 GB VRAM hardware. Best match: Qwen 3.5 9B (score: 97).

374

Models tested

247

Can run

16 GB

VRAM

112

Best tok/s

Tier Distribution

S 11
A 49
B 36
C 151
F 127
S: 11A: 49B: 36C: 151F: 127
S

S Tier -- Perfect Fit (11 models)

These models run flawlessly with headroom to spare.

πŸ‘ Alibaba
Qwen 3.5 9B
S97
9B10.2 GB112 tok/s58K ctx
dense
S95
8B9.6 GB126 tok/s63K ctx
dense
S94
14B13.5 GB73 tok/s33K ctx
dense
πŸ‘ Microsoft
Phi-4-reasoning-plus 14B
S93
14.7B14.5 GB66 tok/s24K ctx
dense
πŸ‘ Alibaba
Qwen 3.5 4B
S91
4B7.1 GB76 tok/s81K ctx
dense
πŸ‘ NVIDIA
Nemotron Nano 8B
S89
8B9.3 GB126 tok/s71K ctx
dense
πŸ‘ Mistral
Ministral 3 14B
S88
14B13.5 GB70 tok/s33K ctx
multimodal
πŸ‘ InternLM
InternVL2 8B
S87
8B9.3 GB126 tok/s8K ctx
dense
πŸ‘ Microsoft
Phi-4 Mini Reasoning 4B
S87
3.8B6.3 GB72 tok/s122K ctx
dense
πŸ‘ Mistral
Ministral 3 8B
S85
8B9.6 GB126 tok/s63K ctx
multimodal
πŸ‘ NVIDIA
Nemotron Nano 9B v2
S85
9B10.4 GB112 tok/s52K ctx
dense
A

A Tier -- Great Fit (49 models)

Excellent performance with comfortable memory margins.

πŸ‘ OpenBMB
MiniCPM-V 2.6 8B
A85
8B9.3 GB126 tok/s2K ctx
dense
A85
14B14.1 GB70 tok/s16K ctx
dense
19B16.5 GB36 tok/s8K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 14B
A84
14B14.0 GB70 tok/s27K ctx
dense
A83
13B12.9 GB76 tok/s33K ctx
dense
πŸ‘ Defog
SQLCoder 7B
A83
7B8.7 GB133 tok/s8K ctx
dense
πŸ‘ DeepSeek
DeepSeek Coder V2 16B
A82
16B15.6 GB126 tok/s18K ctx
moe
A82
4B7.1 GB76 tok/s33K ctx
dense
πŸ‘ Google
Gemma 3 12B
A82
12B14.7 GB55 tok/s20K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 VL 7B
A82
7B7.6 GB133 tok/s33K ctx
dense
A81
7B8.7 GB133 tok/s8K ctx
dense
A81
9B8.6 GB114 tok/s131K ctx
dense
πŸ‘ OpenAI
GPT-OSS 20B
A81
21B17.8 GB61 tok/s5K ctx
moe
πŸ‘ Google
Gemma 4 E4B
A81
8B8.7 GB87 tok/s108K ctx
dense
A80
12B12.3 GB82 tok/s41K ctx
dense
πŸ‘ IBM
Granite Code 8B
A79
8B9.3 GB126 tok/s8K ctx
dense
πŸ‘ Jina AI
Jina Embeddings v3
A79
0.57B5.6 GB11 tok/s8K ctx
dense
πŸ‘ IBM
Granite 4.1 8B
A79
8B9.8 GB126 tok/s56K ctx
dense
A79
7B8.7 GB133 tok/s8K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 7B
A78
7B7.6 GB133 tok/s131K ctx
dense
πŸ‘ DeepSeek
DeepSeek R1 Distill 14B
A78
14B14.0 GB70 tok/s27K ctx
dense
A77
0.57B4.8 GB11 tok/s8K ctx
dense
πŸ‘ BigCode
StarCoder 7B
A77
7B14.1 GB133 tok/s8K ctx
dense
πŸ‘ Meta
CodeLlama 7B Instruct
A77
7B14.6 GB133 tok/s16K ctx
dense
πŸ‘ Mistral AI
Codestral Mamba 7B
A77
7B7.3 GB133 tok/s262K ctx
state-space
7B9.7 GB133 tok/s8K ctx
dense
πŸ‘ Meta
Llama 3.1 8B
A75
8B9.3 GB126 tok/s71K ctx
dense
A75
9B8.6 GB114 tok/s128K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 Coder 3B
A75
3B6.5 GB57 tok/s85K ctx
dense
A75
7B14.6 GB133 tok/s8K ctx
dense
πŸ‘ InternLM
InternLM Chat 7B
A75
7B14.6 GB133 tok/s8K ctx
dense
πŸ‘ WizardLM
WizardMath 7B
A74
7B8.7 GB133 tok/s4K ctx
dense
A74
7B8.7 GB133 tok/s4K ctx
dense
πŸ‘ Mixedbread AI
mxbai Embed Large
A74
0.34B4.7 GB6 tok/s1K ctx
dense
πŸ‘ Mistral
Codestral 2 25.08
A73
22B18.4 GB19 tok/s4K ctx
dense
πŸ‘ Snowflake
Snowflake Arctic Embed L
A73
0.34B4.7 GB6 tok/s1K ctx
dense
πŸ‘ Google
Gemma 4 E2B
A73
5.1B6.1 GB97 tok/s128K ctx
dense
πŸ‘ Microsoft
Phi 3 Mini 3.8B
A72
3.8B10.7 GB72 tok/s31K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 Coder 7B
A72
7B7.6 GB133 tok/s131K ctx
dense
πŸ‘ Google
Gemma 3 4B
A72
4B7.0 GB76 tok/s85K ctx
dense
πŸ‘ LLaVA
LLaVA 1.5 7B
A72
7B14.6 GB133 tok/s4K ctx
dense
πŸ‘ Microsoft
Phi 3.5 Mini 4B
A71
4B10.8 GB76 tok/s30K ctx
dense
πŸ‘ BAAI
BGE Large EN v1.5
A71
0.34B4.7 GB6 tok/s1K ctx
dense
πŸ‘ Meta
Llama 3.2 11B Vision
A71
11B11.2 GB89 tok/s16K ctx
vision
πŸ‘ DeepSeek
DeepSeek R1 Distill 8B
A71
8B9.3 GB126 tok/s33K ctx
dense
πŸ‘ Google
Gemma 2 9B
A71
9B13.1 GB76 tok/s8K ctx
dense
πŸ‘ Microsoft
Phi 4 Mini 4B
A70
4B6.4 GB76 tok/s121K ctx
dense
πŸ‘ MosaicML
MPT-7B-Instruct
A70
7B14.6 GB133 tok/s8K ctx
dense
A70
7B14.6 GB133 tok/s8K ctx
dense
B

B Tier -- Good Fit (36 models)

Solid performance, may need quantization or reduced context.

πŸ‘ IBM
Granite Code 20B
B70
20B17.9 GB28 tok/s7K ctx
dense
7B8.7 GB133 tok/s4K ctx
dense
πŸ‘ Mistral
Ministral 3 3B
B70
3B5.1 GB57 tok/s255K ctx
multimodal
πŸ‘ DeepSeek
DeepSeek R1 Distill 7B
B69
7B7.6 GB133 tok/s33K ctx
dense
πŸ‘ Mistral
Mistral Nemo 12B
B69
12B12.3 GB82 tok/s41K ctx
dense
πŸ‘ Alibaba
Qwen 3.5 2B
B69
2B5.4 GB38 tok/s115K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 3B
B68
3B6.5 GB57 tok/s85K ctx
dense
πŸ‘ Nomic AI
Nomic Embed Text v1.5
B68
0.14B3.3 GB3 tok/s8K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 Coder 14B
B67
14B14.0 GB70 tok/s27K ctx
dense
πŸ‘ TII
Falcon 7B Instruct
B67
7B6.9 GB133 tok/s8K ctx
dense
πŸ‘ 01.AI
Yi Coder 9B
B67
9B9.5 GB114 tok/s87K ctx
dense
πŸ‘ Mistral
Mistral 7B Instruct v0.3
B66
7B8.7 GB133 tok/s8K ctx
dense
πŸ‘ IBM
Granite Code 3B
B66
3B6.8 GB57 tok/s8K ctx
dense
πŸ‘ Alibaba
Qwen 3 1.7B
B65
1.7B5.2 GB32 tok/s33K ctx
dense
πŸ‘ IBM
Granite 4.1 3B
B65
3B5.6 GB57 tok/s131K ctx
dense
πŸ‘ Mistral
Ministral 8B
B64
8B9.6 GB126 tok/s63K ctx
dense
πŸ‘ Microsoft
Phi 3 Medium 14B
B64
14B14.1 GB70 tok/s26K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 Coder 1.5B
B62
1.5B3.8 GB29 tok/s33K ctx
dense
0.02B2.8 GB2 tok/s0K ctx
dense
πŸ‘ Meta
Llama 3.2 3B
B61
3B6.0 GB57 tok/s109K ctx
dense
B59
9B9.5 GB114 tok/s4K ctx
dense
πŸ‘ IBM
Granite 3.1 8B
B59
8B9.3 GB145 tok/s71K ctx
state-space
3B6.3 GB57 tok/s96K ctx
dense
gemma 3 12b it
B56
12B11.2 GB76 tok/s70K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 Math 7B
B56
7B7.6 GB133 tok/s4K ctx
dense
πŸ‘ Unsloth
DeepSeek R1 Distill Qwen 14B
B56
14B12.7 GB65 tok/s48K ctx
dense
πŸ‘ Cohere
Aya Expanse 8B
B56
8B9.3 GB126 tok/s8K ctx
dense
NousResearch Hermes 4 14B
B56
14B12.7 GB65 tok/s48K ctx
dense
B56
7B8.7 GB133 tok/s8K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
B55
14B12.7 GB65 tok/s48K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
B55
10.7B10.3 GB85 tok/s89K ctx
dense
internlm JanusCoder 14B
B55
14B12.7 GB65 tok/s48K ctx
dense
Nous Hermes 2 SOLAR 10.7B
B55
10.7B10.3 GB85 tok/s89K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
B55
14B12.7 GB65 tok/s48K ctx
dense
solar finalised finetuned Model 10.7B i1
B55
10.7B10.3 GB85 tok/s89K ctx
dense
SOLAR 10.7B v1.0
B55
10.7B10.3 GB85 tok/s89K ctx
dense
C

C Tier -- Tight Fit (151 models)

Runs with offloading or significant compromises.

8B9.3 GB126 tok/s33K ctx
dense
Helply 10.2b chat i1
C55
10.2B9.9 GB89 tok/s97K ctx
dense
HelpingAI2.5 10B i1
C54
10B9.8 GB94 tok/s101K ctx
dense
C54
7B14.6 GB133 tok/s4K ctx
dense
πŸ‘ Teknium
OpenHermes 2.5 7B
C54
7B8.7 GB133 tok/s8K ctx
dense
C54
9B9.0 GB105 tok/s122K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C54
9B9.0 GB105 tok/s122K ctx
dense
Qwen3.5 9B
C54
9B9.0 GB105 tok/s122K ctx
dense
C54
7B8.7 GB133 tok/s33K ctx
dense
Yi Coder 9B Chat
C54
9B9.0 GB105 tok/s122K ctx
dense
glm 4 9b chat 1m
C54
9B9.0 GB105 tok/s122K ctx
dense
πŸ‘ DeepSeek
DeepSeek R1 1.5B
C54
1.5B3.8 GB29 tok/s33K ctx
dense
πŸ‘ UC Berkeley
Starling LM 7B
C54
7B8.7 GB133 tok/s8K ctx
dense
Yi 1.5 9B Chat
C54
9B9.0 GB105 tok/s122K ctx
dense
πŸ‘ BigCode
StarCoder2 15B
C54
15B14.5 GB56 tok/s16K ctx
dense
Yi 9B Coder i1
C54
9B9.0 GB105 tok/s122K ctx
dense
HelpingAI2 9B
C54
9B9.0 GB105 tok/s122K ctx
dense
HelpingAI2 9B i1
C53
9B9.0 GB105 tok/s122K ctx
dense
πŸ‘ TinyLlama
TinyLlama 1.1B
C53
1.1B3.5 GB21 tok/s4K ctx
dense
HelpingAI 9B 200k i1
C53
9B9.0 GB105 tok/s122K ctx
dense
HelpingAI 9B i1
C53
9B9.0 GB105 tok/s122K ctx
dense
Meta Llama 3.1 8B Instruct
C53
8B8.3 GB118 tok/s147K ctx
dense
llava llama 3 8b v1 1
C53
8B8.3 GB118 tok/s147K ctx
dense
πŸ‘ Unsloth
DeepSeek R1 0528 Qwen3 8B
C53
8B8.3 GB118 tok/s147K ctx
dense
Meta Llama 3 8B Instruct
C53
8B8.3 GB118 tok/s147K ctx
dense
πŸ‘ Unsloth
DeepSeek R1 Distill Llama 8B
C53
8B8.3 GB118 tok/s147K ctx
dense
Dolphin3.0 Llama3.1 8B
C53
8B8.3 GB118 tok/s147K ctx
dense
Llama 3 8B Instruct 32k v0.1
C53
8B8.3 GB118 tok/s147K ctx
dense
Meta Llama 3.1 8B Instruct
C53
8B8.3 GB118 tok/s147K ctx
dense
vntl llama3 8b v2
C53
8B8.3 GB118 tok/s147K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C53
8B8.3 GB118 tok/s147K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C53
8B8.3 GB118 tok/s147K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C53
8B8.3 GB118 tok/s147K ctx
dense
Hermes 3 Llama 3.1 8B
C53
8B8.3 GB118 tok/s147K ctx
dense
Hermes 2 Pro Llama 3 8B
C53
8B8.3 GB118 tok/s147K ctx
dense
Dolphin3.0 Llama3.1 8B
C53
8B8.3 GB118 tok/s147K ctx
dense
granite 8b code instruct 4k
C53
8B8.3 GB118 tok/s147K ctx
dense
dolphin 2.9.4 llama3.1 8b
C53
8B8.3 GB118 tok/s147K ctx
dense
openchat 3.6 8b 20240522 IMat
C53
8B8.3 GB118 tok/s147K ctx
dense
πŸ‘ Intel
Neural Chat 7B
C53
7B8.7 GB133 tok/s8K ctx
dense
aya expanse 8b
C53
8B8.3 GB118 tok/s147K ctx
dense
dolphin v2 8b abliterated i1
C53
8B8.3 GB118 tok/s147K ctx
dense
aya expanse 8b orthogonal heretic i1
C53
8B8.3 GB118 tok/s147K ctx
dense
EXAONE 3.5 7.8B Instruct
C53
7.8B8.2 GB121 tok/s153K ctx
dense
EXAONE 3.5 7.8B Instruct
C53
7.8B8.2 GB121 tok/s153K ctx
dense
aya expanse 8b orthogonal heretic
C53
8B8.3 GB118 tok/s147K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C53
7.8B8.2 GB121 tok/s153K ctx
dense
exaone 3.0 7.8b it
C53
7.8B8.2 GB121 tok/s153K ctx
dense
internlm2 5 1 8b chat i1
C52
8B8.3 GB118 tok/s147K ctx
dense
internlm3 8b instruct abliterated i1
C52
8B8.3 GB118 tok/s147K ctx
dense
Phi 4 reasoning vision 15B
C52
15B13.4 GB59 tok/s40K ctx
dense
Llama 2 7B Chat
C52
7B7.6 GB133 tok/s180K ctx
dense
StarCoder2 15B
C52
15B13.4 GB59 tok/s40K ctx
dense
Mistral 7B Instruct v0.2
C52
7B7.6 GB133 tok/s180K ctx
dense
Mistral 7B Instruct v0.3
C52
7B7.6 GB133 tok/s180K ctx
dense
πŸ‘ DeepSeek
DeepSeek LLM 7B
C52
7B14.1 GB133 tok/s4K ctx
dense
starcoder2 15b instruct v0.1
C52
15B13.4 GB59 tok/s40K ctx
dense
starcoder2 15b i1
C52
15B13.4 GB59 tok/s40K ctx
dense
starcoder2 15b instruct v0.1
C52
15B13.4 GB59 tok/s40K ctx
dense
Mistral 7B Instruct v0.3
C52
7B7.6 GB133 tok/s180K ctx
dense
Hermes 2 Pro Mistral 7B
C52
7B7.6 GB133 tok/s180K ctx
dense
HelpingAI 15B i1
C52
15B13.4 GB59 tok/s40K ctx
dense
zephyr 7B beta
C52
7B7.6 GB133 tok/s180K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C52
7B7.6 GB133 tok/s180K ctx
dense
Falcon H1R 7B
C52
7B7.6 GB133 tok/s180K ctx
dense
falcon mamba 7b instruct Q4 K M
C52
7B7.6 GB133 tok/s180K ctx
dense
zephyr 7B alpha
C52
7B7.6 GB133 tok/s180K ctx
dense
speechless zephyr code functionary 7b
C52
7B7.6 GB133 tok/s180K ctx
dense
StarCoder2 7B
C52
7B7.6 GB133 tok/s180K ctx
dense
japanese stablelm instruct gamma 7B
C52
7B7.6 GB133 tok/s180K ctx
dense
Falcon H1 7B Instruct
C52
7B7.6 GB133 tok/s180K ctx
dense
πŸ‘ Unsloth
Falcon H1R 7B
C52
7B7.6 GB133 tok/s180K ctx
dense
Mamba Codestral 7B v0.1
C52
7B7.6 GB133 tok/s180K ctx
dense
stabilityai japanese stablelm base gamma 7b
C52
7B7.6 GB133 tok/s180K ctx
dense
baichuan2 7b chat
C52
7B7.6 GB133 tok/s180K ctx
dense
DiscoPOP zephyr 7b gemma
C52
7B7.6 GB133 tok/s180K ctx
dense
starcoder2 7b
C52
7B7.6 GB133 tok/s180K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C52
7B7.6 GB133 tok/s180K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C52
7B7.6 GB133 tok/s180K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C52
7B7.6 GB133 tok/s180K ctx
dense
internlm2 math plus 7b IMat
C52
7B7.6 GB133 tok/s180K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C52
7B7.6 GB133 tok/s180K ctx
dense
internlm2 5 7b chat i1
C52
7B7.6 GB133 tok/s180K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C52
7B7.6 GB133 tok/s180K ctx
dense
MD Judge v0 2 internlm2 7b i1
C52
7B7.6 GB133 tok/s180K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C52
7B7.6 GB133 tok/s180K ctx
dense
jointpreferences mistral 7b sft helpful
C52
7B7.6 GB133 tok/s180K ctx
dense
zephyr 7b dpo full i1
C52
7B7.6 GB133 tok/s180K ctx
dense
blossom v3 baichuan2 7b i1
C52
7B7.6 GB133 tok/s180K ctx
dense
blossom v1 baichuan 7b i1
C51
7B7.6 GB133 tok/s180K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 1.5B
C51
1.5B3.8 GB29 tok/s131K ctx
dense
πŸ‘ NVIDIA
Nemotron Mini 4B
C51
4B6.9 GB76 tok/s4K ctx
dense
Yi 1.5 6B Chat
C51
6B6.9 GB114 tok/s224K ctx
dense
C51
6B7.1 GB114 tok/s4K ctx
dense
stablelm 2 zephyr 1 6b
C51
6B6.9 GB114 tok/s224K ctx
dense
Yi 1.5 6B Chat
C51
6B6.9 GB114 tok/s224K ctx
dense
stablelm 2 1 6b chat imatrix
C51
6B6.9 GB114 tok/s224K ctx
dense
πŸ‘ BigCode
StarCoder2 7B
C51
7B7.3 GB133 tok/s16K ctx
dense
πŸ‘ Google
Gemma 2 2B
C51
2B5.3 GB38 tok/s8K ctx
dense
HelpingAI2 6B
C51
6B6.9 GB114 tok/s224K ctx
dense
HelpingAI2 6B i1
C51
6B6.9 GB114 tok/s224K ctx
dense
Codestral RAG 19B Pruned i1
C50
19B16.3 GB34 tok/s14K ctx
dense
HelpingAI2.5 5B i1
C50
5B6.1 GB95 tok/s285K ctx
dense
πŸ‘ Google
Gemma 3 1B
C49
1B3.5 GB19 tok/s33K ctx
dense
πŸ‘ Mistral AI
Codestral 22B
C49
22B18.4 GB20 tok/s4K ctx
dense
C49
4B5.4 GB76 tok/s378K ctx
dense
gemma 3 4b it
C49
4B5.4 GB76 tok/s378K ctx
dense
gemma 3 4b it
C49
4B5.4 GB76 tok/s378K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 Coder 0.5B
C48
0.5B3.0 GB10 tok/s131K ctx
dense
Llama 3.2 3B Instruct
C47
3B5.0 GB57 tok/s516K ctx
dense
πŸ‘ Qwen
Qwen2.5 3B Instruct
C47
3B4.7 GB57 tok/s531K ctx
dense
Llama 3.2 3B Instruct
C47
3B4.7 GB57 tok/s531K ctx
dense
Ministral 3 3B Instruct 2512
C47
3B4.7 GB57 tok/s531K ctx
dense
HELVETE 3B
C47
3B4.7 GB57 tok/s531K ctx
dense
Hermes 3 Llama 3.2 3B
C46
3B4.7 GB57 tok/s531K ctx
dense
stablelm zephyr 3b
C46
3B4.7 GB57 tok/s531K ctx
dense
StarCoder2 3B
C46
3B4.7 GB57 tok/s531K ctx
dense
πŸ‘ Alibaba
Qwen 3 0.6B
C46
0.6B3.7 GB11 tok/s33K ctx
dense
AI21 Jamba Reasoning 3B
C46
3B4.7 GB57 tok/s531K ctx
dense
stablelm 3b 4e1t
C46
3B4.7 GB57 tok/s531K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C46
3B4.7 GB57 tok/s531K ctx
dense
πŸ‘ Meta
Llama 3.2 1B
C46
1B3.6 GB19 tok/s128K ctx
dense
ai21labs AI21 Jamba2 3B
C46
3B4.7 GB57 tok/s531K ctx
dense
HelpingAI 3B hindi i1
C46
3B4.7 GB57 tok/s531K ctx
dense
AI21 Jamba2 3B
C46
3B4.7 GB57 tok/s531K ctx
dense
HelpingAI 3B hindi
C46
3B4.7 GB57 tok/s531K ctx
dense
AI21 Jamba2 3B i1
C46
3B4.7 GB57 tok/s531K ctx
dense
πŸ‘ BigCode
StarCoder2 3B
C45
3B4.8 GB57 tok/s16K ctx
dense
gemma 2 2b it
C45
2B4.4 GB38 tok/s810K ctx
dense
EXAONE 3.5 2.4B Instruct
C45
2.4B4.2 GB46 tok/s685K ctx
dense
C45
2B4.0 GB38 tok/s838K ctx
dense
Gemmasutra Mini 2B v1
C45
2B4.0 GB38 tok/s838K ctx
dense
gemma 2 2b it
C44
2B4.0 GB38 tok/s838K ctx
dense
πŸ‘ Alibaba
Qwen 3.5 0.6B
C44
0.6B3.7 GB11 tok/s131K ctx
dense
πŸ‘ Qwen
Qwen2.5 1.5B Instruct
C43
1.5B3.6 GB29 tok/s1146K ctx
dense
πŸ‘ Unsloth
DeepSeek R1 Distill Qwen 1.5B
C43
1.5B3.6 GB29 tok/s1146K ctx
dense
Yi Coder 1.5B Chat
C43
1.5B3.6 GB29 tok/s1146K ctx
dense
stablelm 2 zephyr 1.6b
C43
1.6B3.7 GB30 tok/s1069K ctx
dense
logos16v2 stablelm2 1.6b i1
C43
1.6B3.7 GB30 tok/s1069K ctx
dense
Yi Coder 1.5B
C43
1.5B3.6 GB29 tok/s1146K ctx
dense
πŸ‘ Unsloth
Falcon H1 1.5B Instruct
C43
1.5B3.6 GB29 tok/s1146K ctx
dense
TinyLlama 1.1B Chat v1.0
C42
1.1B3.3 GB21 tok/s1592K ctx
dense
EXAONE 4.0 1.2B
C42
1.2B3.4 GB23 tok/s1453K ctx
dense
Llama 3.2 1B Instruct Q8 0
C42
1B3.4 GB19 tok/s1731K ctx
dense
TinyLlama 1.1B Chat v0.3
C42
1.1B3.3 GB21 tok/s1592K ctx
dense
πŸ‘ TinyLlama
TinyLlama 1.1B Chat v0.6
C41
1.1B3.3 GB21 tok/s1592K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 0.5B
C41
0.5B3.0 GB10 tok/s131K ctx
dense
Llama 3.2 1B Instruct
C41
1B3.2 GB19 tok/s1760K ctx
dense
gemma 3 1b it
C41
1B3.2 GB19 tok/s1760K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
C41
1.1B3.3 GB21 tok/s1592K ctx
dense
Falcon3 1B Instruct abliterated
C41
1B3.2 GB19 tok/s1760K ctx
dense
F

F Tier -- Can't Run (127 models)

Too heavy for this hardware.

internlm2 5 20b chat
D40
20B17.0 GB29 tok/s9K ctx
dense
internlm2 limarp chat 20b
D40
20B17.0 GB29 tok/s9K ctx
dense
internlm2 math plus 20b i1
D40
20B17.0 GB29 tok/s9K ctx
dense
Codestral 21B Pruned i1
D39
21B17.8 GB24 tok/s4K ctx
dense
Codestral 22B v0.1
D39
22B18.5 GB21 tok/s4K ctx
dense
Codestral 22B v0.1
D39
22B18.5 GB21 tok/s4K ctx
dense
SmolVLM 500M Instruct
D39
0.5B3.0 GB10 tok/s2094K ctx
dense
Codestral 22B v0.1
D39
22B18.5 GB21 tok/s4K ctx
dense
Codestral 22B v0.1 IMat
D39
22B18.5 GB21 tok/s4K ctx
dense
Codestral 22B v0.1 i1
D39
22B18.5 GB21 tok/s4K ctx
dense
embeddinggemma 300M
D37
0.3B2.8 GB6 tok/s2121K ctx
dense
granite embedding 107m multilingual
D34
0.11B2.7 GB2 tok/s2150K ctx
dense
Falcon H1 Tiny 90M Instruct
D34
0.09B2.7 GB2 tok/s2151K ctx
dense
πŸ‘ Meta
Llama 3.1 70B
F0
70B50.1 GB2 tok/s4K ctx
dense
πŸ‘ Meta
Llama 3.3 70B
F0
70B50.1 GB2 tok/s4K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 32B
F0
32B25.9 GB6 tok/s4K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 72B
F0
72B51.3 GB2 tok/s4K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 Coder 32B
F0
32B25.9 GB6 tok/s4K ctx
dense
F0
32B25.9 GB6 tok/s4K ctx
dense
πŸ‘ Alibaba
Qwen 3 235B A22B
F0
235B148.7 GB2 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen 3 30B A3B
F0
30.5B22.6 GB24 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen3-Coder 30B A3B Instruct
F0
30.5B22.6 GB24 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen3-Coder-Next
F0
80B52.8 GB6 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B298.2 GB2 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen3-VL 30B A3B Instruct
F0
30B22.3 GB35 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen 3.5 27B
F0
27B22.1 GB11 tok/s4K ctx
dense
πŸ‘ Alibaba
Qwen 3.5 35B A3B
F0
35B25.3 GB20 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen 3.6 35B A3B
F0
35B28.0 GB15 tok/s4K ctx
+1moe
πŸ‘ Alibaba
Qwen 3.6 27B
F0
27B19.9 GB9 tok/s4K ctx
+1dense
πŸ‘ Alibaba
Qwen 3.5 122B A10B
F0
122B79.4 GB4 tok/s4K ctx
moe
πŸ‘ Alibaba
Qwen 3.5 397B A17B
F0
397B247.5 GB2 tok/s4K ctx
moe
πŸ‘ Google
Gemma 2 27B
F0
27B30.2 GB4 tok/s4K ctx
dense
πŸ‘ Google
Gemma 3 27B
F0
27B30.2 GB4 tok/s4K ctx
dense
πŸ‘ Mistral
Mistral Small 24B
F0
24B19.6 GB17 tok/s4K ctx
dense
πŸ‘ Mistral
Mistral Small 3.2 24B
F0
24B19.6 GB17 tok/s4K ctx
vision
πŸ‘ Mistral
Mixtral 8x7B
F0
47B33.1 GB6 tok/s4K ctx
moe
πŸ‘ Mistral
Mixtral 8x22B
F0
141B91.9 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek R1 Distill 32B
F0
32B25.9 GB6 tok/s4K ctx
dense
πŸ‘ IBM
Granite 4.1 30B
F0
30B24.7 GB7 tok/s4K ctx
dense
πŸ‘ Cohere
Command R 35B
F0
35B26.3 GB5 tok/s4K ctx
dense
πŸ‘ TII
Falcon 40B Instruct
F0
40B33.1 GB3 tok/s4K ctx
dense
πŸ‘ WizardLM
WizardLM 13B
F0
13B22.6 GB26 tok/s7K ctx
dense
πŸ‘ BigCode
StarCoder 15B
F0
15B27.9 GB13 tok/s4K ctx
dense
πŸ‘ Meta
CodeLlama 13B Instruct
F0
13B22.6 GB26 tok/s7K ctx
dense
πŸ‘ MosaicML
MPT-30B-Instruct
F0
30B47.5 GB3 tok/s4K ctx
dense
πŸ‘ Mistral
Devstral Small 1.1
F0
24B19.6 GB15 tok/s4K ctx
dense
πŸ‘ Mistral
Devstral Small 2 24B Instruct
F0
24B19.6 GB15 tok/s4K ctx
dense
πŸ‘ Mistral
Devstral 2 123B Instruct
F0
123B82.9 GB2 tok/s4K ctx
dense
πŸ‘ Mistral
Mistral Small 4 119B
F0
119B80.5 GB4 tok/s4K ctx
moe
πŸ‘ Mistral
Leanstral 119B A6B
F0
119B83.9 GB3 tok/s4K ctx
moe
πŸ‘ Mistral
Mistral Large 3
F0
675B419.6 GB2 tok/s4K ctx
+1moe
πŸ‘ Mistral
Magistral Small 2507
F0
24B19.6 GB17 tok/s4K ctx
dense
744B475.4 GB2 tok/s4K ctx
moe
F0
754B481.5 GB2 tok/s4K ctx
moe
1000B619.9 GB2 tok/s4K ctx
moe
1000B619.9 GB2 tok/s4K ctx
+1moe
πŸ‘ Moonshot AI
Kimi Linear 48B A3B
F0
48B32.7 GB2 tok/s4K ctx
linear
πŸ‘ Nous Research
Nous Hermes 1.0
F0
9B20.2 GB50 tok/s10K ctx
dense
πŸ‘ Nous Research
Nous Dolphin 13B
F0
13B24.1 GB20 tok/s5K ctx
dense
πŸ‘ Baichuan
Baichuan 13B
F0
13B24.1 GB20 tok/s5K ctx
dense
πŸ‘ Cerebras
Cerebras-GPT 13B
F0
13B21.6 GB25 tok/s7K ctx
dense
πŸ‘ Stability AI
StableLM 2 12B
F0
12B23.3 GB19 tok/s4K ctx
dense
πŸ‘ InternLM
InternLM 20B
F0
20B35.2 GB6 tok/s4K ctx
dense
πŸ‘ 01.AI
Yi 34B Chat
F0
34B26.9 GB5 tok/s4K ctx
dense
πŸ‘ DeepSeek
DeepSeek V3 671B
F0
671B471.4 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek V3.1 671B
F0
671B471.4 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek V4 Pro
F0
1600B866.4 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek V4 Flash
F0
284B161.8 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek R1 671B
F0
671B471.4 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek Coder V2 236B
F0
236B205.1 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek V2.5 236B
F0
236B205.1 GB2 tok/s4K ctx
moe
πŸ‘ DeepSeek
DeepSeek LLM 67B
F0
67B49.2 GB2 tok/s4K ctx
dense
πŸ‘ Meta
Llama 4 Scout 17B 16E
F0
109B71.9 GB3 tok/s4K ctx
moe
πŸ‘ Meta
Llama 4 Maverick 17B 128E
F0
400B249.4 GB2 tok/s4K ctx
moe
πŸ‘ Cohere
Command R+ 104B
F0
104B69.4 GB2 tok/s4K ctx
dense
πŸ‘ Cohere
Command A 111B
F0
111B74.1 GB2 tok/s4K ctx
dense
πŸ‘ 01.AI
Yi 1.5 34B
F0
34B26.9 GB5 tok/s4K ctx
dense
πŸ‘ Mistral AI
Pixtral Large 124B
F0
124B83.5 GB2 tok/s4K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 VL 72B
F0
72B51.3 GB2 tok/s4K ctx
dense
πŸ‘ Alibaba
Qwen 2.5 Math 72B
F0
72B51.3 GB2 tok/s4K ctx
dense
πŸ‘ NVIDIA
Nemotron 70B
F0
70B50.1 GB2 tok/s4K ctx
dense
πŸ‘ LLaVA
LLaVA 1.6 13B
F0
13B22.6 GB26 tok/s4K ctx
dense
πŸ‘ LMSYS
Vicuna 13B
F0
13B22.6 GB26 tok/s4K ctx
dense
F0
32B25.9 GB6 tok/s4K ctx
dense
πŸ‘ NVIDIA
Nemotron 3 Nano 30B
F0
30B23.2 GB8 tok/s4K ctx
dense
πŸ‘ LG AI
EXAONE 4.0 32B
F0
32B25.9 GB6 tok/s4K ctx
dense
24B19.6 GB17 tok/s4K ctx
dense
πŸ‘ Meta
Llama 3.1 405B
F0
405B257.2 GB2 tok/s4K ctx
dense
πŸ‘ DeepSeek
DeepSeek R1 Distill 70B
F0
70B50.1 GB2 tok/s4K ctx
dense
πŸ‘ IBM
Granite Code 34B
F0
34B26.9 GB5 tok/s4K ctx
dense
πŸ‘ OpenAI
GPT-OSS 120B
F0
117B78.8 GB2 tok/s4K ctx
dense
πŸ‘ Cohere
Aya Expanse 32B
F0
32B24.5 GB7 tok/s4K ctx
dense
πŸ‘ Mistral AI
Mistral Small 3.1 24B
F0
24B19.6 GB17 tok/s4K ctx
dense
πŸ‘ Google
Gemma 4 26B A4B
F0
25.2B21.5 GB35 tok/s4K ctx
moe
πŸ‘ Google
Gemma 4 31B
F0
30.7B35.9 GB2 tok/s4K ctx
dense
πŸ‘ DeepSeek
DeepSeek V3.2
F0
671B412.3 GB2 tok/s4K ctx
moe
πŸ‘ NVIDIA
Nemotron Cascade 2 30B A3B
F0
30B23.7 GB30 tok/s4K ctx
moe
MiniMax M2.7
F0
230B146.6 GB2 tok/s4K ctx
moe
Solar Open 100B
F0
100B75.2 GB2 tok/s4K ctx
dense
Baichuan M2 32B Q4 K M
F0
32B25.8 GB6 tok/s4K ctx
dense
baichuan inc Baichuan M2 32B
F0
32B25.8 GB6 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B20.0 GB15 tok/s4K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
F0
24B20.0 GB15 tok/s4K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
F0
48B37.4 GB2 tok/s4K ctx
dense
EXAONE 4.0 32B
F0
32B25.8 GB6 tok/s4K ctx
dense
K EXAONE 236B A23B
F0
236B174.1 GB2 tok/s4K ctx
dense
Qwen3.5 35B A3B
F0
35B28.0 GB4 tok/s4K ctx
dense
gemma 3 27b it
F0
27B22.1 GB10 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F0
70B53.4 GB2 tok/s4K ctx
dense
Mistral Small 24B Instruct 2501
F0
24B20.0 GB15 tok/s4K ctx
dense
mistral small 3.1 24b instruct 2503 hf
F0
24B20.0 GB15 tok/s4K ctx
dense
aya expanse 32b heretic MPOA i1
F0
32B25.8 GB6 tok/s4K ctx
dense
Baichuan M3 235B
F0
235B173.4 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0
235B173.4 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F0
72B54.9 GB2 tok/s4K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
F0
24B20.0 GB15 tok/s4K ctx
dense
Solar Open 100B i1
F0
100B75.2 GB2 tok/s4K ctx
dense
Solar Open 69B REAP i1
F0
69B52.7 GB2 tok/s4K ctx
dense
Hermes 4.3 36B
F0
36B28.7 GB4 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F0
70B53.4 GB2 tok/s4K ctx
dense
πŸ‘ Unsloth
gemma 3 27b it
F0
27B22.1 GB10 tok/s4K ctx
dense
πŸ‘ Unsloth
Mistral Small 3.2 24B Instruct 2506
F0
24B20.0 GB15 tok/s4K ctx
dense
πŸ‘ Unsloth
Qwen3.5 122B A10B
F0
122B76.6 GB2 tok/s4K ctx
dense
πŸ‘ Unsloth
Qwen3.5 27B
F0
27B22.1 GB10 tok/s4K ctx
dense
πŸ‘ Unsloth
Qwen3.5 35B A3B
F0
35B28.0 GB4 tok/s4K ctx
dense
πŸ‘ Unsloth
Qwen3.5 397B A17B
F0
397B291.2 GB2 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B20.0 GB15 tok/s4K ctx
dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

RTX 4060 Ti 16GB

16 GB VRAM

View tier list

RTX 4070 Ti Super 16GB

16 GB VRAM

View tier list

RTX 4080 Super 16GB

16 GB VRAM

View tier list

RTX 4090 Laptop 16GB

16 GB VRAM

View tier list
Full RTX 5070 Ti 16GB pageCompare this hardware