VOOZH about

URL: https://willitrunai.com/my-results/rtx-4090-laptop-16gb

⇱ RTX 4090 Laptop 16GB AI Tier List: 247 models ranked | WillItRunAI


AI Compatibility Tier List

RTX 4090 Laptop 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

87

Best tok/s

Tier Distribution

S 10
A 48
B 31
C 158
F 127
S: 10A: 48B: 31C: 158F: 127
S

S Tier -- Perfect Fit (10 models)

These models run flawlessly with headroom to spare.

👁 Alibaba
Qwen 3.5 9B
S97
9B10.2 GB87 tok/s58K ctx
dense
👁 Alibaba
Qwen 3 8B
S95
8B9.6 GB98 tok/s63K ctx
dense
👁 Alibaba
Qwen 3 14B
S94
14B13.5 GB67 tok/s33K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
S92
14.7B14.5 GB57 tok/s24K ctx
dense
👁 Alibaba
Qwen 3.5 4B
S90
4B7.1 GB64 tok/s81K ctx
dense
👁 NVIDIA
Nemotron Nano 8B
S89
8B9.3 GB93 tok/s71K ctx
dense
👁 Mistral
Ministral 3 14B
S88
14B13.5 GB61 tok/s33K ctx
multimodal
👁 InternLM
InternVL2 8B
S87
8B9.3 GB93 tok/s8K ctx
dense
👁 Microsoft
Phi-4 Mini Reasoning 4B
S86
3.8B6.3 GB61 tok/s122K ctx
dense
👁 Mistral
Ministral 3 8B
S85
8B9.6 GB93 tok/s63K ctx
multimodal
A

A Tier -- Great Fit (48 models)

Excellent performance with comfortable memory margins.

👁 NVIDIA
Nemotron Nano 9B v2
A85
9B10.4 GB83 tok/s52K ctx
dense
👁 OpenBMB
MiniCPM-V 2.6 8B
A85
8B9.3 GB93 tok/s2K ctx
dense
A84
14B14.1 GB61 tok/s16K ctx
dense
👁 Alibaba
Qwen 2.5 14B
A83
14B14.0 GB61 tok/s27K ctx
dense
👁 Defog
SQLCoder 7B
A83
7B8.7 GB107 tok/s8K ctx
dense
A83
19B16.5 GB25 tok/s8K ctx
dense
👁 AllenAI
OLMo 2 13B
A83
13B12.9 GB66 tok/s33K ctx
dense
👁 DeepSeek
DeepSeek Coder V2 16B
A82
16B15.6 GB101 tok/s18K ctx
moe
👁 Alibaba
Qwen 2.5 VL 7B
A82
7B7.6 GB108 tok/s33K ctx
dense
👁 Alibaba
Qwen 3 4B
A82
4B7.1 GB64 tok/s33K ctx
dense
👁 Google
Gemma 3 12B
A82
12B14.7 GB51 tok/s20K ctx
dense
👁 Magistral AI
Magistral 7B
A81
7B8.7 GB107 tok/s8K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
A81
9B8.6 GB85 tok/s131K ctx
dense
👁 OpenAI
GPT-OSS 20B
A80
21B17.8 GB48 tok/s5K ctx
moe
👁 Google
Gemma 4 E4B
A80
8B8.7 GB68 tok/s108K ctx
dense
👁 Mistral AI
Pixtral 12B
A80
12B12.3 GB71 tok/s41K ctx
dense
👁 IBM
Granite Code 8B
A79
8B9.3 GB93 tok/s8K ctx
dense
👁 IBM
Granite 4.1 8B
A79
8B9.8 GB93 tok/s56K ctx
dense
👁 Jina AI
Jina Embeddings v3
A79
0.57B5.6 GB9 tok/s8K ctx
dense
👁 DevStral AI
DevStral 7B
A79
7B8.7 GB107 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 7B
A78
7B7.6 GB108 tok/s131K ctx
dense
👁 BigCode
StarCoder 7B
A77
7B14.1 GB99 tok/s8K ctx
dense
👁 Meta
CodeLlama 7B Instruct
A77
7B14.6 GB99 tok/s16K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 14B
A77
14B14.0 GB61 tok/s27K ctx
dense
👁 BAAI
BGE M3
A77
0.57B4.8 GB9 tok/s8K ctx
dense
👁 Mistral AI
Codestral Mamba 7B
A77
7B7.3 GB112 tok/s262K ctx
state-space
A75
7B9.7 GB107 tok/s8K ctx
dense
👁 Meta
Llama 3.1 8B
A75
8B9.3 GB93 tok/s71K ctx
dense
👁 Zhipu
GLM-4 9B
A75
9B8.6 GB85 tok/s128K ctx
dense
👁 InternLM
InternLM 7B
A75
7B14.6 GB99 tok/s8K ctx
dense
👁 InternLM
InternLM Chat 7B
A75
7B14.6 GB99 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 3B
A74
3B6.5 GB48 tok/s85K ctx
dense
👁 WizardLM
WizardMath 7B
A74
7B8.7 GB107 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
A74
7B8.7 GB107 tok/s4K ctx
dense
👁 Mixedbread AI
mxbai Embed Large
A73
0.34B4.7 GB5 tok/s1K ctx
dense
👁 Google
Gemma 4 E2B
A73
5.1B6.1 GB82 tok/s128K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
A73
0.34B4.7 GB5 tok/s1K ctx
dense
👁 Mistral
Codestral 2 25.08
A72
22B18.4 GB14 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 7B
A72
7B7.6 GB108 tok/s131K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
A72
3.8B10.7 GB61 tok/s31K ctx
dense
👁 LLaVA
LLaVA 1.5 7B
A72
7B14.6 GB99 tok/s4K ctx
dense
👁 Google
Gemma 3 4B
A71
4B7.0 GB64 tok/s85K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
A71
4B10.8 GB64 tok/s30K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 8B
A71
8B9.3 GB93 tok/s33K ctx
dense
👁 BAAI
BGE Large EN v1.5
A71
0.34B4.7 GB5 tok/s1K ctx
dense
👁 Meta
Llama 3.2 11B Vision
A71
11B11.2 GB78 tok/s16K ctx
vision
👁 MosaicML
MPT-7B-Instruct
A70
7B14.6 GB99 tok/s8K ctx
dense
👁 Baichuan
Baichuan 7B
A70
7B14.6 GB99 tok/s8K ctx
dense
B

B Tier -- Good Fit (31 models)

Solid performance, may need quantization or reduced context.

👁 Google
Gemma 2 9B
B70
9B13.1 GB59 tok/s8K ctx
dense
👁 Microsoft
Phi 4 Mini 4B
B70
4B6.4 GB64 tok/s121K ctx
dense
7B8.7 GB107 tok/s4K ctx
dense
👁 Mistral
Ministral 3 3B
B69
3B5.1 GB48 tok/s255K ctx
multimodal
👁 DeepSeek
DeepSeek R1 Distill 7B
B69
7B7.6 GB108 tok/s33K ctx
dense
👁 IBM
Granite Code 20B
B69
20B17.9 GB20 tok/s7K ctx
dense
👁 Mistral
Mistral Nemo 12B
B68
12B12.3 GB71 tok/s41K ctx
dense
👁 Alibaba
Qwen 3.5 2B
B68
2B5.4 GB32 tok/s115K ctx
dense
👁 Nomic AI
Nomic Embed Text v1.5
B67
0.14B3.3 GB2 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 3B
B67
3B6.5 GB48 tok/s85K ctx
dense
👁 TII
Falcon 7B Instruct
B67
7B6.9 GB109 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 14B
B67
14B14.0 GB61 tok/s27K ctx
dense
👁 01.AI
Yi Coder 9B
B67
9B9.5 GB84 tok/s87K ctx
dense
👁 Mistral
Mistral 7B Instruct v0.3
B66
7B8.7 GB107 tok/s8K ctx
dense
👁 IBM
Granite Code 3B
B65
3B6.8 GB48 tok/s8K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B65
1.7B5.2 GB27 tok/s33K ctx
dense
👁 IBM
Granite 4.1 3B
B64
3B5.6 GB48 tok/s131K ctx
dense
👁 Mistral
Ministral 8B
B64
8B9.6 GB93 tok/s63K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
B64
14B14.1 GB61 tok/s26K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 1.5B
B61
1.5B3.8 GB24 tok/s33K ctx
dense
B61
0.02B2.8 GB2 tok/s0K ctx
dense
👁 Meta
Llama 3.2 3B
B60
3B6.0 GB48 tok/s109K ctx
dense
👁 IBM
Granite 3.1 8B
B59
8B9.3 GB117 tok/s71K ctx
state-space
👁 01.AI
Yi 1.5 9B
B59
9B9.5 GB84 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
B56
7B7.6 GB108 tok/s4K ctx
dense
B56
3B6.3 GB48 tok/s96K ctx
dense
gemma 3 12b it
B56
12B11.2 GB66 tok/s70K ctx
dense
👁 Cohere
Aya Expanse 8B
B56
8B9.3 GB93 tok/s8K ctx
dense
👁 OpenChat
OpenChat 7B
B56
7B8.7 GB107 tok/s8K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
B55
14B12.7 GB57 tok/s48K ctx
dense
NousResearch Hermes 4 14B
B55
14B12.7 GB57 tok/s48K ctx
dense
C

C Tier -- Tight Fit (158 models)

Runs with offloading or significant compromises.

GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
C55
14B12.7 GB57 tok/s48K ctx
dense
8B9.3 GB93 tok/s33K ctx
dense
internlm JanusCoder 14B
C55
14B12.7 GB57 tok/s48K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C55
10.7B10.3 GB74 tok/s89K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
C55
14B12.7 GB57 tok/s48K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C55
10.7B10.3 GB74 tok/s89K ctx
dense
solar finalised finetuned Model 10.7B i1
C55
10.7B10.3 GB74 tok/s89K ctx
dense
SOLAR 10.7B v1.0
C55
10.7B10.3 GB74 tok/s89K ctx
dense
👁 LMSYS
Vicuna 7B
C54
7B14.6 GB99 tok/s4K ctx
dense
👁 Teknium
OpenHermes 2.5 7B
C54
7B8.7 GB107 tok/s8K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
C54
7B8.7 GB107 tok/s33K ctx
dense
Helply 10.2b chat i1
C54
10.2B9.9 GB78 tok/s97K ctx
dense
👁 UC Berkeley
Starling LM 7B
C54
7B8.7 GB107 tok/s8K ctx
dense
👁 Unsloth
Qwen3.5 9B
C54
9B9.0 GB77 tok/s122K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C54
9B9.0 GB77 tok/s122K ctx
dense
Qwen3.5 9B
C54
9B9.0 GB77 tok/s122K ctx
dense
HelpingAI2.5 10B i1
C54
10B9.8 GB70 tok/s101K ctx
dense
Yi Coder 9B Chat
C53
9B9.0 GB77 tok/s122K ctx
dense
glm 4 9b chat 1m
C53
9B9.0 GB77 tok/s122K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
C53
1.5B3.8 GB24 tok/s33K ctx
dense
Yi 1.5 9B Chat
C53
9B9.0 GB77 tok/s122K ctx
dense
👁 BigCode
StarCoder2 15B
C53
15B14.5 GB49 tok/s16K ctx
dense
Meta Llama 3.1 8B Instruct
C53
8B8.3 GB87 tok/s147K ctx
dense
llava llama 3 8b v1 1
C53
8B8.3 GB87 tok/s147K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
C53
8B8.3 GB87 tok/s147K ctx
dense
Meta Llama 3 8B Instruct
C53
8B8.3 GB87 tok/s147K ctx
dense
Yi 9B Coder i1
C53
9B9.0 GB77 tok/s122K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
C53
8B8.3 GB87 tok/s147K ctx
dense
Dolphin3.0 Llama3.1 8B
C53
8B8.3 GB87 tok/s147K ctx
dense
Llama 3 8B Instruct 32k v0.1
C53
8B8.3 GB87 tok/s147K ctx
dense
Meta Llama 3.1 8B Instruct
C53
8B8.3 GB87 tok/s147K ctx
dense
vntl llama3 8b v2
C53
8B8.3 GB87 tok/s147K ctx
dense
HelpingAI2 9B
C53
9B9.0 GB77 tok/s122K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C53
8B8.3 GB87 tok/s147K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C53
8B8.3 GB87 tok/s147K ctx
dense
HelpingAI2 9B i1
C53
9B9.0 GB77 tok/s122K ctx
dense
HelpingAI 9B 200k i1
C53
9B9.0 GB77 tok/s122K ctx
dense
👁 TinyLlama
TinyLlama 1.1B
C53
1.1B3.5 GB18 tok/s4K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C53
8B8.3 GB87 tok/s147K ctx
dense
HelpingAI 9B i1
C53
9B9.0 GB77 tok/s122K ctx
dense
Hermes 3 Llama 3.1 8B
C53
8B8.3 GB87 tok/s147K ctx
dense
👁 Intel
Neural Chat 7B
C53
7B8.7 GB107 tok/s8K ctx
dense
Hermes 2 Pro Llama 3 8B
C53
8B8.3 GB87 tok/s147K ctx
dense
Dolphin3.0 Llama3.1 8B
C53
8B8.3 GB87 tok/s147K ctx
dense
granite 8b code instruct 4k
C53
8B8.3 GB87 tok/s147K ctx
dense
dolphin 2.9.4 llama3.1 8b
C53
8B8.3 GB87 tok/s147K ctx
dense
openchat 3.6 8b 20240522 IMat
C53
8B8.3 GB87 tok/s147K ctx
dense
aya expanse 8b
C53
8B8.3 GB87 tok/s147K ctx
dense
dolphin v2 8b abliterated i1
C53
8B8.3 GB87 tok/s147K ctx
dense
EXAONE 3.5 7.8B Instruct
C53
7.8B8.2 GB89 tok/s153K ctx
dense
EXAONE 3.5 7.8B Instruct
C53
7.8B8.2 GB89 tok/s153K ctx
dense
aya expanse 8b orthogonal heretic i1
C53
8B8.3 GB87 tok/s147K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C53
7.8B8.2 GB89 tok/s153K ctx
dense
exaone 3.0 7.8b it
C52
7.8B8.2 GB89 tok/s153K ctx
dense
aya expanse 8b orthogonal heretic
C52
8B8.3 GB87 tok/s147K ctx
dense
Llama 2 7B Chat
C52
7B7.6 GB99 tok/s180K ctx
dense
internlm2 5 1 8b chat i1
C52
8B8.3 GB87 tok/s147K ctx
dense
internlm3 8b instruct abliterated i1
C52
8B8.3 GB87 tok/s147K ctx
dense
Mistral 7B Instruct v0.2
C52
7B7.6 GB99 tok/s180K ctx
dense
Mistral 7B Instruct v0.3
C52
7B7.6 GB99 tok/s180K ctx
dense
👁 DeepSeek
DeepSeek LLM 7B
C52
7B14.1 GB99 tok/s4K ctx
dense
Mistral 7B Instruct v0.3
C52
7B7.6 GB99 tok/s180K ctx
dense
Hermes 2 Pro Mistral 7B
C52
7B7.6 GB99 tok/s180K ctx
dense
zephyr 7B beta
C52
7B7.6 GB99 tok/s180K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C52
7B7.6 GB99 tok/s180K ctx
dense
Falcon H1R 7B
C52
7B7.6 GB99 tok/s180K ctx
dense
Phi 4 reasoning vision 15B
C52
15B13.4 GB52 tok/s40K ctx
dense
StarCoder2 15B
C52
15B13.4 GB52 tok/s40K ctx
dense
falcon mamba 7b instruct Q4 K M
C52
7B7.6 GB112 tok/s180K ctx
dense
zephyr 7B alpha
C52
7B7.6 GB99 tok/s180K ctx
dense
speechless zephyr code functionary 7b
C52
7B7.6 GB99 tok/s180K ctx
dense
StarCoder2 7B
C52
7B7.6 GB99 tok/s180K ctx
dense
japanese stablelm instruct gamma 7B
C52
7B7.6 GB99 tok/s180K ctx
dense
Falcon H1 7B Instruct
C52
7B7.6 GB99 tok/s180K ctx
dense
👁 Unsloth
Falcon H1R 7B
C52
7B7.6 GB99 tok/s180K ctx
dense
starcoder2 15b instruct v0.1
C52
15B13.4 GB52 tok/s40K ctx
dense
Mamba Codestral 7B v0.1
C52
7B7.6 GB112 tok/s180K ctx
dense
starcoder2 15b i1
C52
15B13.4 GB52 tok/s40K ctx
dense
stabilityai japanese stablelm base gamma 7b
C52
7B7.6 GB99 tok/s180K ctx
dense
baichuan2 7b chat
C52
7B7.6 GB99 tok/s180K ctx
dense
starcoder2 15b instruct v0.1
C52
15B13.4 GB52 tok/s40K ctx
dense
DiscoPOP zephyr 7b gemma
C52
7B7.6 GB95 tok/s180K ctx
dense
starcoder2 7b
C52
7B7.6 GB99 tok/s180K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C52
7B7.6 GB99 tok/s180K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C52
7B7.6 GB99 tok/s180K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C52
7B7.6 GB99 tok/s180K ctx
dense
internlm2 math plus 7b IMat
C52
7B7.6 GB99 tok/s180K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C52
7B7.6 GB99 tok/s180K ctx
dense
internlm2 5 7b chat i1
C52
7B7.6 GB99 tok/s180K ctx
dense
HelpingAI 15B i1
C52
15B13.4 GB52 tok/s40K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C52
7B7.6 GB99 tok/s180K ctx
dense
MD Judge v0 2 internlm2 7b i1
C52
7B7.6 GB99 tok/s180K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C52
7B7.6 GB95 tok/s180K ctx
dense
jointpreferences mistral 7b sft helpful
C52
7B7.6 GB99 tok/s180K ctx
dense
zephyr 7b dpo full i1
C52
7B7.6 GB99 tok/s180K ctx
dense
blossom v3 baichuan2 7b i1
C52
7B7.6 GB99 tok/s180K ctx
dense
blossom v1 baichuan 7b i1
C51
7B7.6 GB99 tok/s180K ctx
dense
Yi 1.5 6B Chat
C51
6B6.9 GB96 tok/s224K ctx
dense
👁 01.AI
Yi 1.5 6B
C51
6B7.1 GB96 tok/s4K ctx
dense
stablelm 2 zephyr 1 6b
C51
6B6.9 GB96 tok/s224K ctx
dense
Yi 1.5 6B Chat
C51
6B6.9 GB96 tok/s224K ctx
dense
stablelm 2 1 6b chat imatrix
C51
6B6.9 GB96 tok/s224K ctx
dense
👁 BigCode
StarCoder2 7B
C51
7B7.3 GB108 tok/s16K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
C51
1.5B3.8 GB24 tok/s131K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
C51
4B6.9 GB64 tok/s4K ctx
dense
HelpingAI2 6B
C51
6B6.9 GB96 tok/s224K ctx
dense
HelpingAI2 6B i1
C51
6B6.9 GB96 tok/s224K ctx
dense
👁 Google
Gemma 2 2B
C50
2B5.3 GB32 tok/s8K ctx
dense
HelpingAI2.5 5B i1
C49
5B6.1 GB80 tok/s285K ctx
dense
Codestral RAG 19B Pruned i1
C49
19B16.3 GB24 tok/s14K ctx
dense
👁 Google
Gemma 3 1B
C49
1B3.5 GB16 tok/s33K ctx
dense
👁 Unsloth
Qwen3.5 4B
C48
4B5.4 GB64 tok/s378K ctx
dense
gemma 3 4b it
C48
4B5.4 GB64 tok/s378K ctx
dense
👁 Mistral AI
Codestral 22B
C48
22B18.4 GB15 tok/s4K ctx
dense
gemma 3 4b it
C48
4B5.4 GB64 tok/s378K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C47
0.5B3.0 GB8 tok/s131K ctx
dense
Llama 3.2 3B Instruct
C47
3B5.0 GB48 tok/s516K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C46
3B4.7 GB48 tok/s531K ctx
dense
Llama 3.2 3B Instruct
C46
3B4.7 GB48 tok/s531K ctx
dense
Ministral 3 3B Instruct 2512
C46
3B4.7 GB48 tok/s531K ctx
dense
HELVETE 3B
C46
3B4.7 GB48 tok/s531K ctx
dense
Hermes 3 Llama 3.2 3B
C46
3B4.7 GB48 tok/s531K ctx
dense
stablelm zephyr 3b
C46
3B4.7 GB48 tok/s531K ctx
dense
👁 Alibaba
Qwen 3 0.6B
C46
0.6B3.7 GB10 tok/s33K ctx
dense
StarCoder2 3B
C46
3B4.7 GB48 tok/s531K ctx
dense
AI21 Jamba Reasoning 3B
C46
3B4.7 GB48 tok/s531K ctx
dense
stablelm 3b 4e1t
C46
3B4.7 GB48 tok/s531K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C46
3B4.7 GB48 tok/s531K ctx
dense
👁 Meta
Llama 3.2 1B
C46
1B3.6 GB16 tok/s128K ctx
dense
ai21labs AI21 Jamba2 3B
C46
3B4.7 GB48 tok/s531K ctx
dense
HelpingAI 3B hindi i1
C46
3B4.7 GB48 tok/s531K ctx
dense
AI21 Jamba2 3B
C46
3B4.7 GB48 tok/s531K ctx
dense
HelpingAI 3B hindi
C46
3B4.7 GB48 tok/s531K ctx
dense
AI21 Jamba2 3B i1
C46
3B4.7 GB48 tok/s531K ctx
dense
👁 BigCode
StarCoder2 3B
C45
3B4.8 GB48 tok/s16K ctx
dense
gemma 2 2b it
C45
2B4.4 GB32 tok/s810K ctx
dense
EXAONE 3.5 2.4B Instruct
C44
2.4B4.2 GB38 tok/s685K ctx
dense
👁 Google
gemma 2b
C44
2B4.0 GB32 tok/s838K ctx
dense
Gemmasutra Mini 2B v1
C44
2B4.0 GB32 tok/s838K ctx
dense
gemma 2 2b it
C44
2B4.0 GB32 tok/s838K ctx
dense
👁 Alibaba
Qwen 3.5 0.6B
C44
0.6B3.7 GB10 tok/s131K ctx
dense
👁 Qwen
Qwen2.5 1.5B Instruct
C43
1.5B3.6 GB24 tok/s1146K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B
C43
1.5B3.6 GB24 tok/s1146K ctx
dense
Yi Coder 1.5B Chat
C42
1.5B3.6 GB24 tok/s1146K ctx
dense
stablelm 2 zephyr 1.6b
C42
1.6B3.7 GB26 tok/s1069K ctx
dense
logos16v2 stablelm2 1.6b i1
C42
1.6B3.7 GB26 tok/s1069K ctx
dense
Yi Coder 1.5B
C42
1.5B3.6 GB24 tok/s1146K ctx
dense
👁 Unsloth
Falcon H1 1.5B Instruct
C42
1.5B3.6 GB24 tok/s1146K ctx
dense
TinyLlama 1.1B Chat v1.0
C41
1.1B3.3 GB18 tok/s1592K ctx
dense
EXAONE 4.0 1.2B
C41
1.2B3.4 GB19 tok/s1453K ctx
dense
Llama 3.2 1B Instruct Q8 0
C41
1B3.4 GB16 tok/s1731K ctx
dense
TinyLlama 1.1B Chat v0.3
C41
1.1B3.3 GB18 tok/s1592K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
C41
1.1B3.3 GB18 tok/s1592K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
C41
0.5B3.0 GB8 tok/s131K ctx
dense
Llama 3.2 1B Instruct
C41
1B3.2 GB16 tok/s1760K ctx
dense
gemma 3 1b it
C41
1B3.2 GB16 tok/s1760K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
C41
1.1B3.3 GB18 tok/s1592K ctx
dense
Falcon3 1B Instruct abliterated
C40
1B3.2 GB16 tok/s1760K ctx
dense
F

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

Too heavy for this hardware.

internlm2 5 20b chat
D39
20B17.0 GB20 tok/s9K ctx
dense
internlm2 limarp chat 20b
D39
20B17.0 GB20 tok/s9K ctx
dense
internlm2 math plus 20b i1
D38
20B17.0 GB20 tok/s9K ctx
dense
SmolVLM 500M Instruct
D38
0.5B3.0 GB8 tok/s2094K ctx
dense
Codestral 21B Pruned i1
D38
21B17.8 GB17 tok/s4K ctx
dense
Codestral 22B v0.1
D38
22B18.5 GB14 tok/s4K ctx
dense
Codestral 22B v0.1
D38
22B18.5 GB14 tok/s4K ctx
dense
Codestral 22B v0.1
D38
22B18.5 GB14 tok/s4K ctx
dense
Codestral 22B v0.1 IMat
D38
22B18.5 GB14 tok/s4K ctx
dense
Codestral 22B v0.1 i1
D37
22B18.5 GB14 tok/s4K ctx
dense
embeddinggemma 300M
D37
0.3B2.8 GB5 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
👁 Meta
Llama 3.1 70B
F0
70B50.1 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.3 70B
F0
70B50.1 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 32B
F0
32B25.9 GB4 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 72B
F0
72B51.3 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 32B
F0
32B25.9 GB4 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 32B
F0
32B25.9 GB4 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
F0
235B148.7 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3 30B A3B
F0
30.5B22.6 GB18 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 30B A3B Instruct
F0
30.5B22.6 GB18 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder-Next
F0
80B52.8 GB5 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B298.2 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-VL 30B A3B Instruct
F0
30B22.3 GB27 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 27B
F0
27B22.1 GB8 tok/s4K ctx
dense
👁 Alibaba
Qwen 3.5 35B A3B
F0
35B25.3 GB20 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.6 35B A3B
F0
35B28.0 GB15 tok/s4K ctx
+1moe
👁 Alibaba
Qwen 3.6 27B
F0
27B19.9 GB7 tok/s4K ctx
+1dense
👁 Alibaba
Qwen 3.5 122B A10B
F0
122B79.4 GB3 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B247.5 GB2 tok/s4K ctx
moe
👁 Google
Gemma 2 27B
F0
27B30.2 GB3 tok/s4K ctx
dense
👁 Google
Gemma 3 27B
F0
27B30.2 GB3 tok/s4K ctx
dense
👁 Mistral
Mistral Small 24B
F0
24B19.6 GB12 tok/s4K ctx
dense
👁 Mistral
Mistral Small 3.2 24B
F0
24B19.6 GB12 tok/s4K ctx
vision
👁 Mistral
Mixtral 8x7B
F0
47B33.1 GB5 tok/s4K ctx
moe
👁 Mistral
Mixtral 8x22B
F0
141B91.9 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 Distill 32B
F0
32B25.9 GB4 tok/s4K ctx
dense
👁 IBM
Granite 4.1 30B
F0
30B24.7 GB5 tok/s4K ctx
dense
👁 Cohere
Command R 35B
F0
35B26.3 GB4 tok/s4K ctx
dense
👁 TII
Falcon 40B Instruct
F0
40B33.1 GB2 tok/s4K ctx
dense
👁 WizardLM
WizardLM 13B
F0
13B22.6 GB22 tok/s7K ctx
dense
👁 BigCode
StarCoder 15B
F0
15B27.9 GB10 tok/s4K ctx
dense
👁 Meta
CodeLlama 13B Instruct
F0
13B22.6 GB22 tok/s7K ctx
dense
👁 MosaicML
MPT-30B-Instruct
F0
30B47.5 GB2 tok/s4K ctx
dense
👁 Mistral
Devstral Small 1.1
F0
24B19.6 GB12 tok/s4K ctx
dense
👁 Mistral
Devstral Small 2 24B Instruct
F0
24B19.6 GB12 tok/s4K ctx
dense
👁 Mistral
Devstral 2 123B Instruct
F0
123B82.9 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 4 119B
F0
119B80.5 GB3 tok/s4K ctx
moe
👁 Mistral
Leanstral 119B A6B
F0
119B83.9 GB3 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B419.6 GB2 tok/s4K ctx
+1moe
👁 Mistral
Magistral Small 2507
F0
24B19.6 GB12 tok/s4K ctx
dense
F0
744B475.4 GB2 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B481.5 GB2 tok/s4K ctx
moe
F0
1000B619.9 GB2 tok/s4K ctx
moe
F0
1000B619.9 GB2 tok/s4K ctx
+1moe
👁 Moonshot AI
Kimi Linear 48B A3B
F0
48B32.7 GB2 tok/s4K ctx
linear
👁 Nous Research
Nous Hermes 1.0
F0
9B20.2 GB36 tok/s10K ctx
dense
👁 Nous Research
Nous Dolphin 13B
F0
13B24.1 GB17 tok/s5K ctx
dense
👁 Baichuan
Baichuan 13B
F0
13B24.1 GB17 tok/s5K ctx
dense
👁 Cerebras
Cerebras-GPT 13B
F0
13B21.6 GB21 tok/s7K ctx
dense
👁 Stability AI
StableLM 2 12B
F0
12B23.3 GB18 tok/s4K ctx
dense
👁 InternLM
InternLM 20B
F0
20B35.2 GB4 tok/s4K ctx
dense
👁 01.AI
Yi 34B Chat
F0
34B26.9 GB4 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3 671B
F0
671B471.4 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B471.4 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B866.4 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Flash
F0
284B161.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B471.4 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B205.1 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B205.1 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek LLM 67B
F0
67B49.2 GB2 tok/s4K ctx
dense
👁 Meta
Llama 4 Scout 17B 16E
F0
109B71.9 GB2 tok/s4K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B249.4 GB2 tok/s4K ctx
moe
👁 Cohere
Command R+ 104B
F0
104B69.4 GB2 tok/s4K ctx
dense
👁 Cohere
Command A 111B
F0
111B74.1 GB2 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 34B
F0
34B26.9 GB4 tok/s4K ctx
dense
👁 Mistral AI
Pixtral Large 124B
F0
124B83.5 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 VL 72B
F0
72B51.3 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
F0
72B51.3 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 70B
F0
70B50.1 GB2 tok/s4K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
F0
13B22.6 GB22 tok/s4K ctx
dense
👁 LMSYS
Vicuna 13B
F0
13B22.6 GB22 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 32B
F0
32B25.9 GB4 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 3 Nano 30B
F0
30B23.2 GB5 tok/s4K ctx
dense
👁 LG AI
EXAONE 4.0 32B
F0
32B25.9 GB4 tok/s4K ctx
dense
F0
24B19.6 GB12 tok/s4K ctx
dense
👁 Meta
Llama 3.1 405B
F0
405B257.2 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
F0
70B50.1 GB2 tok/s4K ctx
dense
👁 IBM
Granite Code 34B
F0
34B26.9 GB4 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 120B
F0
117B78.8 GB2 tok/s4K ctx
dense
👁 Cohere
Aya Expanse 32B
F0
32B24.5 GB5 tok/s4K ctx
dense
👁 Mistral AI
Mistral Small 3.1 24B
F0
24B19.6 GB12 tok/s4K ctx
dense
👁 Google
Gemma 4 26B A4B
F0
25.2B21.5 GB27 tok/s4K ctx
moe
👁 Google
Gemma 4 31B
F0
30.7B35.9 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B412.3 GB2 tok/s4K ctx
moe
👁 NVIDIA
Nemotron Cascade 2 30B A3B
F0
30B23.7 GB23 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 GB4 tok/s4K ctx
dense
baichuan inc Baichuan M2 32B
F0
32B25.8 GB4 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B20.0 GB11 tok/s4K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
F0
24B20.0 GB11 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 GB4 tok/s4K ctx
dense
K EXAONE 236B A23B
F0
236B174.1 GB2 tok/s4K ctx
dense
Qwen3.5 35B A3B
F0
35B28.0 GB3 tok/s4K ctx
dense
gemma 3 27b it
F0
27B22.1 GB7 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 GB11 tok/s4K ctx
dense
mistral small 3.1 24b instruct 2503 hf
F0
24B20.0 GB11 tok/s4K ctx
dense
aya expanse 32b heretic MPOA i1
F0
32B25.8 GB4 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 GB11 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 GB3 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F0
70B53.4 GB2 tok/s4K ctx
dense
👁 Unsloth
gemma 3 27b it
F0
27B22.1 GB7 tok/s4K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
F0
24B20.0 GB11 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
F0
122B76.6 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 27B
F0
27B22.1 GB7 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
F0
35B28.0 GB3 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 397B A17B
F0
397B291.2 GB2 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B20.0 GB11 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 5070 Ti 16GB

16 GB VRAM

View tier list
Full RTX 4090 Laptop 16GB pageCompare this hardware