VOOZH about

URL: https://willitrunai.com/my-results/rtx-4000-ada-20gb

⇱ RTX 4000 Ada 20GB AI Tier List: 279 models ranked | WillItRunAI


AI Compatibility Tier List

RTX 4000 Ada 20GB

374 AI models ranked by how well they run on your 20 GB VRAM hardware. Best match: Qwen 3 14B (score: 94).

374

Models tested

279

Can run

20 GB

VRAM

36

Best tok/s

Tier Distribution

S 13
A 54
B 36
C 176
F 95
S: 13A: 54B: 36C: 176F: 95
S

S Tier -- Perfect Fit (13 models)

These models run flawlessly with headroom to spare.

👁 Alibaba
Qwen 3 14B
S94
14B13.9 GB36 tok/s56K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
S93
14.7B14.9 GB34 tok/s33K ctx
dense
👁 Alibaba
Qwen 3.5 9B
S93
9B10.6 GB55 tok/s85K ctx
dense
👁 Alibaba
Qwen 3 8B
S91
8B10.0 GB62 tok/s89K ctx
dense
👁 OpenAI
GPT-OSS 20B
S91
21B18.2 GB54 tok/s28K ctx
moe
👁 Mistral
Magistral Small 2507
S91
24B20.0 GB21 tok/s16K ctx
dense
👁 Mistral
Devstral Small 2 24B Instruct
S90
24B20.0 GB21 tok/s16K ctx
dense
👁 Alibaba
Qwen 3.6 27B
S89
27B20.3 GB10 tok/s10K ctx
+1dense
👁 Mistral
Ministral 3 14B
S89
14B13.9 GB35 tok/s56K ctx
multimodal
👁 Mistral
Devstral Small 1.1
S89
24B20.0 GB21 tok/s16K ctx
dense
👁 Alibaba
Qwen 3.5 4B
S88
4B7.5 GB56 tok/s107K ctx
dense
👁 NVIDIA
Nemotron Nano 8B
S86
8B9.7 GB62 tok/s100K ctx
dense
S85
14B14.5 GB35 tok/s16K ctx
dense
A

A Tier -- Great Fit (54 models)

Excellent performance with comfortable memory margins.

👁 Alibaba
Qwen 2.5 14B
A85
14B14.4 GB36 tok/s47K ctx
dense
👁 DeepSeek
DeepSeek Coder V2 16B
A85
16B16.0 GB69 tok/s36K ctx
moe
👁 Microsoft
Phi-4 Mini Reasoning 4B
A84
3.8B6.7 GB53 tok/s131K ctx
dense
👁 InternLM
InternVL2 8B
A83
8B9.7 GB62 tok/s8K ctx
dense
👁 Mistral
Codestral 2 25.08
A83
22B18.8 GB20 tok/s24K ctx
dense
A83
19B16.9 GB26 tok/s8K ctx
dense
👁 Mistral
Mistral Small 3.2 24B
A83
24B20.0 GB21 tok/s16K ctx
vision
👁 Google
Gemma 3 12B
A83
12B15.1 GB31 tok/s32K ctx
dense
👁 Alibaba
Qwen3-Coder 30B A3B Instruct
A83
30.5B23.0 GB24 tok/s4K ctx
moe
A82
24B20.0 GB21 tok/s16K ctx
dense
👁 Alibaba
Qwen3-VL 30B A3B Instruct
A82
30B22.7 GB25 tok/s4K ctx
moe
👁 Mistral
Ministral 3 8B
A82
8B10.0 GB62 tok/s89K ctx
multimodal
👁 OpenBMB
MiniCPM-V 2.6 8B
A82
8B9.7 GB62 tok/s2K ctx
dense
👁 NVIDIA
Nemotron Nano 9B v2
A81
9B10.8 GB55 tok/s76K ctx
dense
👁 Mistral
Mistral Small 24B
A81
24B20.0 GB21 tok/s16K ctx
dense
👁 Defog
SQLCoder 7B
A80
7B9.1 GB71 tok/s8K ctx
dense
👁 Mistral AI
Mistral Small 3.1 24B
A80
24B20.0 GB21 tok/s16K ctx
dense
👁 AllenAI
OLMo 2 13B
A80
13B13.3 GB38 tok/s33K ctx
dense
👁 Alibaba
Qwen 3 30B A3B
A80
30.5B23.0 GB24 tok/s4K ctx
moe
👁 Alibaba
Qwen 3 4B
A80
4B7.5 GB56 tok/s33K ctx
dense
👁 Alibaba
Qwen 3.5 27B
A80
27B22.5 GB11 tok/s4K ctx
dense
👁 IBM
Granite Code 20B
A79
20B18.3 GB25 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 VL 7B
A79
7B8.0 GB71 tok/s33K ctx
dense
👁 BigCode
StarCoder 7B
A79
7B14.5 GB66 tok/s8K ctx
dense
👁 Meta
CodeLlama 7B Instruct
A79
7B15.0 GB66 tok/s16K ctx
dense
👁 Magistral AI
Magistral 7B
A79
7B9.1 GB71 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 14B
A78
14B14.4 GB36 tok/s33K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
A78
9B9.0 GB56 tok/s131K ctx
dense
👁 Jina AI
Jina Embeddings v3
A77
0.57B6.0 GB8 tok/s8K ctx
dense
👁 Google
Gemma 4 E4B
A77
8B9.1 GB47 tok/s128K ctx
dense
👁 Mistral AI
Pixtral 12B
A76
12B12.7 GB41 tok/s64K ctx
dense
👁 InternLM
InternLM 7B
A76
7B15.0 GB66 tok/s8K ctx
dense
👁 InternLM
InternLM Chat 7B
A76
7B15.0 GB66 tok/s8K ctx
dense
👁 IBM
Granite Code 8B
A76
8B9.7 GB62 tok/s8K ctx
dense
👁 DevStral AI
DevStral 7B
A76
7B9.1 GB71 tok/s8K ctx
dense
👁 IBM
Granite 4.1 8B
A76
8B10.2 GB62 tok/s80K ctx
dense
👁 BAAI
BGE M3
A76
0.57B5.2 GB8 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 7B
A76
7B8.0 GB71 tok/s131K ctx
dense
👁 Google
Gemma 4 26B A4B
A75
25.2B21.9 GB28 tok/s8K ctx
moe
👁 Mistral AI
Codestral Mamba 7B
A75
7B7.7 GB76 tok/s262K ctx
state-space
👁 LLaVA
LLaVA 1.5 7B
A74
7B15.0 GB66 tok/s4K ctx
dense
A72
7B10.1 GB71 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 3B
A72
3B6.9 GB42 tok/s111K ctx
dense
👁 Mixedbread AI
mxbai Embed Large
A72
0.34B5.1 GB5 tok/s1K ctx
dense
👁 Meta
Llama 3.1 8B
A72
8B9.7 GB62 tok/s100K ctx
dense
👁 MosaicML
MPT-7B-Instruct
A72
7B15.0 GB66 tok/s8K ctx
dense
👁 Baichuan
Baichuan 7B
A72
7B15.0 GB66 tok/s8K ctx
dense
👁 Nous Research
Nous Hermes 1.0
A71
9B20.6 GB36 tok/s15K ctx
dense
👁 WizardLM
WizardMath 7B
A71
7B9.1 GB71 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
A71
7B9.1 GB71 tok/s4K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
A71
0.34B5.1 GB5 tok/s1K ctx
dense
👁 Zhipu
GLM-4 9B
A71
9B9.0 GB56 tok/s128K ctx
dense
👁 Google
Gemma 4 E2B
A71
5.1B6.5 GB71 tok/s128K ctx
dense
👁 NVIDIA
Nemotron 3 Nano 30B
A71
30B23.6 GB9 tok/s4K ctx
dense
B

B Tier -- Good Fit (36 models)

Solid performance, may need quantization or reduced context.

👁 Alibaba
Qwen 2.5 Coder 7B
B70
7B8.0 GB71 tok/s131K ctx
dense
👁 BAAI
BGE Large EN v1.5
B70
0.34B5.1 GB5 tok/s1K ctx
dense
👁 Google
Gemma 3 4B
B69
4B7.4 GB56 tok/s113K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
B69
3.8B11.1 GB53 tok/s40K ctx
dense
👁 Google
Gemma 2 9B
B68
9B13.5 GB41 tok/s8K ctx
dense
👁 Microsoft
Phi 4 Mini 4B
B68
4B6.8 GB56 tok/s128K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 14B
B68
14B14.4 GB36 tok/s47K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
B68
4B11.2 GB56 tok/s40K ctx
dense
👁 Mistral
Ministral 3 3B
B68
3B5.5 GB42 tok/s262K ctx
multimodal
👁 DeepSeek
DeepSeek R1 Distill 8B
B68
8B9.7 GB62 tok/s33K ctx
dense
7B9.1 GB71 tok/s4K ctx
dense
👁 Nomic AI
Nomic Embed Text v1.5
B67
0.14B3.7 GB2 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 7B
B67
7B8.0 GB71 tok/s33K ctx
dense
👁 Alibaba
Qwen 3.5 2B
B67
2B5.8 GB28 tok/s131K ctx
dense
👁 Meta
Llama 3.2 11B Vision
B66
11B11.6 GB45 tok/s16K ctx
vision
👁 Alibaba
Qwen 2.5 3B
B66
3B6.9 GB42 tok/s111K ctx
dense
👁 Mistral
Mistral Nemo 12B
B65
12B12.7 GB41 tok/s64K ctx
dense
👁 TII
Falcon 7B Instruct
B65
7B7.3 GB72 tok/s8K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
B65
14B14.5 GB35 tok/s45K ctx
dense
👁 Meta
CodeLlama 13B Instruct
B64
13B23.0 GB20 tok/s12K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B63
1.7B5.6 GB24 tok/s33K ctx
dense
👁 IBM
Granite Code 3B
B63
3B7.2 GB42 tok/s8K ctx
dense
👁 01.AI
Yi Coder 9B
B63
9B9.9 GB56 tok/s127K ctx
dense
👁 Mistral
Mistral 7B Instruct v0.3
B63
7B9.1 GB71 tok/s8K ctx
dense
👁 IBM
Granite 4.1 3B
B63
3B6.0 GB42 tok/s131K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
B62
13B23.0 GB20 tok/s4K ctx
dense
B61
0.02B3.2 GB2 tok/s0K ctx
dense
👁 Mistral
Ministral 8B
B61
8B10.0 GB62 tok/s89K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 1.5B
B60
1.5B4.2 GB21 tok/s33K ctx
dense
👁 WizardLM
WizardLM 13B
B60
13B23.0 GB20 tok/s8K ctx
dense
👁 LMSYS
Vicuna 13B
B60
13B23.0 GB20 tok/s4K ctx
dense
👁 Mistral AI
Codestral 22B
B59
22B18.8 GB21 tok/s24K ctx
dense
👁 Meta
Llama 3.2 3B
B59
3B6.4 GB42 tok/s128K ctx
dense
👁 LMSYS
Vicuna 7B
B56
7B15.0 GB66 tok/s4K ctx
dense
👁 IBM
Granite 3.1 8B
B56
8B9.7 GB71 tok/s100K ctx
state-space
👁 01.AI
Yi 1.5 9B
B55
9B9.9 GB56 tok/s4K ctx
dense
C

C Tier -- Tight Fit (176 models)

Runs with offloading or significant compromises.

👁 Cerebras
Cerebras-GPT 13B
C55
13B22.0 GB19 tok/s13K ctx
dense
👁 BigCode
StarCoder2 15B
C55
15B14.9 GB29 tok/s16K ctx
dense
C54
3B6.7 GB42 tok/s125K ctx
dense
👁 DeepSeek
DeepSeek LLM 7B
C54
7B14.5 GB66 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
C54
7B8.0 GB71 tok/s4K ctx
dense
Phi 4 reasoning vision 15B
C53
15B13.8 GB31 tok/s72K ctx
dense
StarCoder2 15B
C53
15B13.8 GB31 tok/s72K ctx
dense
starcoder2 15b instruct v0.1
C53
15B13.8 GB31 tok/s72K ctx
dense
👁 OpenChat
OpenChat 7B
C53
7B9.1 GB71 tok/s8K ctx
dense
starcoder2 15b i1
C53
15B13.8 GB31 tok/s72K ctx
dense
starcoder2 15b instruct v0.1
C53
15B13.8 GB31 tok/s72K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
C53
14B13.1 GB33 tok/s83K ctx
dense
HelpingAI 15B i1
C53
15B13.8 GB31 tok/s72K ctx
dense
👁 Cohere
Aya Expanse 8B
C53
8B9.7 GB62 tok/s8K ctx
dense
NousResearch Hermes 4 14B
C52
14B13.1 GB33 tok/s83K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
C52
1.5B4.2 GB21 tok/s33K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
C52
14B13.1 GB33 tok/s83K ctx
dense
internlm JanusCoder 14B
C52
14B13.1 GB33 tok/s83K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
C52
14B13.1 GB33 tok/s83K ctx
dense
👁 TinyLlama
TinyLlama 1.1B
C52
1.1B3.9 GB15 tok/s4K ctx
dense
8B9.7 GB62 tok/s33K ctx
dense
gemma 3 12b it
C52
12B11.6 GB38 tok/s111K ctx
dense
👁 Teknium
OpenHermes 2.5 7B
C52
7B9.1 GB71 tok/s8K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
C51
7B9.1 GB71 tok/s33K ctx
dense
👁 UC Berkeley
Starling LM 7B
C51
7B9.1 GB71 tok/s8K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C51
10.7B10.7 GB43 tok/s135K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C51
10.7B10.7 GB43 tok/s135K ctx
dense
solar finalised finetuned Model 10.7B i1
C51
10.7B10.7 GB43 tok/s135K ctx
dense
SOLAR 10.7B v1.0
C50
10.7B10.7 GB43 tok/s135K ctx
dense
👁 Unsloth
Qwen3.5 9B
C50
9B9.4 GB51 tok/s176K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C50
9B9.4 GB51 tok/s176K ctx
dense
Qwen3.5 9B
C50
9B9.4 GB51 tok/s176K ctx
dense
Yi Coder 9B Chat
C50
9B9.4 GB51 tok/s176K ctx
dense
glm 4 9b chat 1m
C50
9B9.4 GB51 tok/s176K ctx
dense
Helply 10.2b chat i1
C50
10.2B10.3 GB45 tok/s146K ctx
dense
HelpingAI2.5 10B i1
C50
10B10.2 GB46 tok/s150K ctx
dense
👁 Intel
Neural Chat 7B
C50
7B9.1 GB71 tok/s8K ctx
dense
Meta Llama 3.1 8B Instruct
C50
8B8.7 GB58 tok/s209K ctx
dense
llava llama 3 8b v1 1
C50
8B8.7 GB58 tok/s209K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
C50
8B8.7 GB58 tok/s209K ctx
dense
Yi 1.5 9B Chat
C50
9B9.4 GB51 tok/s176K ctx
dense
Meta Llama 3 8B Instruct
C50
8B8.7 GB58 tok/s209K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
C50
8B8.7 GB58 tok/s209K ctx
dense
Dolphin3.0 Llama3.1 8B
C50
8B8.7 GB58 tok/s209K ctx
dense
Llama 3 8B Instruct 32k v0.1
C50
8B8.7 GB58 tok/s209K ctx
dense
Meta Llama 3.1 8B Instruct
C50
8B8.7 GB58 tok/s209K ctx
dense
vntl llama3 8b v2
C50
8B8.7 GB58 tok/s209K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C50
8B8.7 GB58 tok/s209K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
C50
1.5B4.2 GB21 tok/s131K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C50
8B8.7 GB58 tok/s209K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C50
8B8.7 GB58 tok/s209K ctx
dense
Yi 9B Coder i1
C50
9B9.4 GB51 tok/s176K ctx
dense
Hermes 3 Llama 3.1 8B
C50
8B8.7 GB58 tok/s209K ctx
dense
Llama 2 7B Chat
C50
7B8.0 GB66 tok/s250K ctx
dense
falcon mamba 7b instruct Q4 K M
C50
7B8.0 GB76 tok/s250K ctx
dense
Mistral 7B Instruct v0.2
C50
7B8.0 GB66 tok/s250K ctx
dense
HelpingAI2 9B
C50
9B9.4 GB51 tok/s176K ctx
dense
Hermes 2 Pro Llama 3 8B
C50
8B8.7 GB58 tok/s209K ctx
dense
Dolphin3.0 Llama3.1 8B
C50
8B8.7 GB58 tok/s209K ctx
dense
Mistral 7B Instruct v0.3
C50
7B8.0 GB66 tok/s250K ctx
dense
granite 8b code instruct 4k
C50
8B8.7 GB58 tok/s209K ctx
dense
dolphin 2.9.4 llama3.1 8b
C50
8B8.7 GB58 tok/s209K ctx
dense
HelpingAI2 9B i1
C50
9B9.4 GB51 tok/s176K ctx
dense
HelpingAI 9B 200k i1
C50
9B9.4 GB51 tok/s176K ctx
dense
HelpingAI 9B i1
C50
9B9.4 GB51 tok/s176K ctx
dense
openchat 3.6 8b 20240522 IMat
C50
8B8.7 GB58 tok/s209K ctx
dense
aya expanse 8b
C49
8B8.7 GB58 tok/s209K ctx
dense
EXAONE 3.5 7.8B Instruct
C49
7.8B8.6 GB59 tok/s216K ctx
dense
Mamba Codestral 7B v0.1
C49
7B8.0 GB76 tok/s250K ctx
dense
dolphin v2 8b abliterated i1
C49
8B8.7 GB58 tok/s209K ctx
dense
EXAONE 3.5 7.8B Instruct
C49
7.8B8.6 GB59 tok/s216K ctx
dense
👁 01.AI
Yi 1.5 6B
C49
6B7.5 GB83 tok/s4K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C49
7.8B8.6 GB59 tok/s216K ctx
dense
aya expanse 8b orthogonal heretic i1
C49
8B8.7 GB58 tok/s209K ctx
dense
Mistral 7B Instruct v0.3
C49
7B8.0 GB66 tok/s250K ctx
dense
exaone 3.0 7.8b it
C49
7.8B8.6 GB59 tok/s216K ctx
dense
Hermes 2 Pro Mistral 7B
C49
7B8.0 GB66 tok/s250K ctx
dense
zephyr 7B beta
C49
7B8.0 GB66 tok/s250K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C49
7B8.0 GB66 tok/s250K ctx
dense
aya expanse 8b orthogonal heretic
C49
8B8.7 GB58 tok/s209K ctx
dense
Falcon H1R 7B
C49
7B8.0 GB66 tok/s250K ctx
dense
zephyr 7B alpha
C49
7B8.0 GB66 tok/s250K ctx
dense
speechless zephyr code functionary 7b
C49
7B8.0 GB66 tok/s250K ctx
dense
Yi 1.5 6B Chat
C49
6B7.3 GB77 tok/s306K ctx
dense
internlm2 5 1 8b chat i1
C49
8B8.7 GB58 tok/s209K ctx
dense
internlm3 8b instruct abliterated i1
C49
8B8.7 GB58 tok/s209K ctx
dense
StarCoder2 7B
C49
7B8.0 GB66 tok/s250K ctx
dense
japanese stablelm instruct gamma 7B
C49
7B8.0 GB66 tok/s250K ctx
dense
stablelm 2 zephyr 1 6b
C49
6B7.3 GB77 tok/s306K ctx
dense
Falcon H1 7B Instruct
C49
7B8.0 GB66 tok/s250K ctx
dense
👁 Unsloth
Falcon H1R 7B
C49
7B8.0 GB66 tok/s250K ctx
dense
Codestral 22B v0.1
C49
22B18.9 GB21 tok/s23K ctx
dense
Codestral RAG 19B Pruned i1
C49
19B16.7 GB24 tok/s40K ctx
dense
Codestral 22B v0.1
C49
22B18.9 GB21 tok/s23K ctx
dense
internlm2 5 20b chat
C49
20B17.4 GB23 tok/s33K ctx
dense
stabilityai japanese stablelm base gamma 7b
C49
7B8.0 GB66 tok/s250K ctx
dense
baichuan2 7b chat
C49
7B8.0 GB66 tok/s250K ctx
dense
internlm2 limarp chat 20b
C49
20B17.4 GB23 tok/s33K ctx
dense
DiscoPOP zephyr 7b gemma
C49
7B8.0 GB66 tok/s250K ctx
dense
Yi 1.5 6B Chat
C49
6B7.3 GB77 tok/s306K ctx
dense
stablelm 2 1 6b chat imatrix
C49
6B7.3 GB77 tok/s306K ctx
dense
starcoder2 7b
C49
7B8.0 GB66 tok/s250K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C49
7B8.0 GB66 tok/s250K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C49
7B8.0 GB66 tok/s250K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C49
7B8.0 GB66 tok/s250K ctx
dense
internlm2 math plus 20b i1
C49
20B17.4 GB23 tok/s33K ctx
dense
internlm2 math plus 7b IMat
C49
7B8.0 GB66 tok/s250K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C49
7B8.0 GB66 tok/s250K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
C49
4B7.3 GB56 tok/s4K ctx
dense
internlm2 5 7b chat i1
C49
7B8.0 GB66 tok/s250K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C49
7B8.0 GB66 tok/s250K ctx
dense
MD Judge v0 2 internlm2 7b i1
C49
7B8.0 GB66 tok/s250K ctx
dense
Codestral 22B v0.1
C49
22B18.9 GB21 tok/s23K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C49
7B8.0 GB66 tok/s250K ctx
dense
👁 Google
Gemma 2 2B
C49
2B5.7 GB28 tok/s8K ctx
dense
jointpreferences mistral 7b sft helpful
C49
7B8.0 GB66 tok/s250K ctx
dense
zephyr 7b dpo full i1
C49
7B8.0 GB66 tok/s250K ctx
dense
blossom v3 baichuan2 7b i1
C49
7B8.0 GB66 tok/s250K ctx
dense
blossom v1 baichuan 7b i1
C49
7B8.0 GB66 tok/s250K ctx
dense
Codestral 21B Pruned i1
C49
21B18.2 GB22 tok/s28K ctx
dense
Codestral 22B v0.1 IMat
C49
22B18.9 GB21 tok/s23K ctx
dense
HelpingAI2 6B
C49
6B7.3 GB77 tok/s306K ctx
dense
HelpingAI2 6B i1
C49
6B7.3 GB77 tok/s306K ctx
dense
Codestral 22B v0.1 i1
C49
22B18.9 GB21 tok/s23K ctx
dense
👁 BigCode
StarCoder2 7B
C49
7B7.7 GB72 tok/s16K ctx
dense
👁 Google
Gemma 3 1B
C48
1B3.9 GB14 tok/s33K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
C48
24B20.4 GB14 tok/s14K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C48
24B20.4 GB14 tok/s14K ctx
dense
Mistral Small 24B Instruct 2501
C48
24B20.4 GB14 tok/s14K ctx
dense
mistral small 3.1 24b instruct 2503 hf
C48
24B20.4 GB14 tok/s14K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
C48
24B20.4 GB14 tok/s14K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
C48
24B20.4 GB14 tok/s14K ctx
dense
HelpingAI2.5 5B i1
C47
5B6.5 GB70 tok/s384K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C47
24B20.4 GB14 tok/s14K ctx
dense
👁 Unsloth
Qwen3.5 4B
C47
4B5.8 GB56 tok/s500K ctx
dense
gemma 3 4b it
C47
4B5.8 GB56 tok/s500K ctx
dense
gemma 3 4b it
C47
4B5.8 GB56 tok/s500K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C46
0.5B3.4 GB7 tok/s131K ctx
dense
Llama 3.2 3B Instruct
C45
3B5.4 GB42 tok/s680K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C45
3B5.1 GB42 tok/s695K ctx
dense
👁 Alibaba
Qwen 3 0.6B
C45
0.6B4.1 GB8 tok/s33K ctx
dense
Llama 3.2 3B Instruct
C45
3B5.1 GB42 tok/s695K ctx
dense
Ministral 3 3B Instruct 2512
C45
3B5.1 GB42 tok/s695K ctx
dense
👁 Meta
Llama 3.2 1B
C45
1B4.0 GB14 tok/s128K ctx
dense
HELVETE 3B
C45
3B5.1 GB42 tok/s695K ctx
dense
Hermes 3 Llama 3.2 3B
C45
3B5.1 GB42 tok/s695K ctx
dense
stablelm zephyr 3b
C45
3B5.1 GB42 tok/s695K ctx
dense
StarCoder2 3B
C45
3B5.1 GB42 tok/s695K ctx
dense
AI21 Jamba Reasoning 3B
C45
3B5.1 GB42 tok/s695K ctx
dense
stablelm 3b 4e1t
C44
3B5.1 GB42 tok/s695K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C44
3B5.1 GB42 tok/s695K ctx
dense
ai21labs AI21 Jamba2 3B
C44
3B5.1 GB42 tok/s695K ctx
dense
HelpingAI 3B hindi i1
C44
3B5.1 GB42 tok/s695K ctx
dense
AI21 Jamba2 3B
C44
3B5.1 GB42 tok/s695K ctx
dense
HelpingAI 3B hindi
C44
3B5.1 GB42 tok/s695K ctx
dense
AI21 Jamba2 3B i1
C44
3B5.1 GB42 tok/s695K ctx
dense
gemma 2 2b it
C44
2B4.8 GB28 tok/s1055K ctx
dense
👁 BigCode
StarCoder2 3B
C43
3B5.2 GB42 tok/s16K ctx
dense
EXAONE 3.5 2.4B Instruct
C43
2.4B4.6 GB34 tok/s890K ctx
dense
👁 Google
gemma 2b
C43
2B4.4 GB28 tok/s1084K ctx
dense
Gemmasutra Mini 2B v1
C43
2B4.4 GB28 tok/s1084K ctx
dense
gemma 2 2b it
C43
2B4.4 GB28 tok/s1084K ctx
dense
👁 Alibaba
Qwen 3.5 0.6B
C43
0.6B4.1 GB8 tok/s131K ctx
dense
👁 Qwen
Qwen2.5 1.5B Instruct
C42
1.5B4.0 GB21 tok/s1473K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B
C42
1.5B4.0 GB21 tok/s1473K ctx
dense
Yi Coder 1.5B Chat
C42
1.5B4.0 GB21 tok/s1473K ctx
dense
stablelm 2 zephyr 1.6b
C41
1.6B4.1 GB22 tok/s1376K ctx
dense
logos16v2 stablelm2 1.6b i1
C41
1.6B4.1 GB22 tok/s1376K ctx
dense
Yi Coder 1.5B
C41
1.5B4.0 GB21 tok/s1473K ctx
dense
👁 Unsloth
Falcon H1 1.5B Instruct
C41
1.5B4.0 GB21 tok/s1473K ctx
dense
TinyLlama 1.1B Chat v1.0
C40
1.1B3.7 GB15 tok/s2039K ctx
dense
EXAONE 4.0 1.2B
C40
1.2B3.8 GB17 tok/s1862K ctx
dense
Llama 3.2 1B Instruct Q8 0
C40
1B3.8 GB14 tok/s2223K ctx
dense
TinyLlama 1.1B Chat v0.3
C40
1.1B3.7 GB15 tok/s2039K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
C40
1.1B3.7 GB15 tok/s2039K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
C40
0.5B3.4 GB7 tok/s131K ctx
dense
F

F Tier -- Can't Run (95 models)

Too heavy for this hardware.

Llama 3.2 1B Instruct
D40
1B3.6 GB14 tok/s2251K ctx
dense
gemma 3 1b it
D40
1B3.6 GB14 tok/s2251K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
D40
1.1B3.7 GB15 tok/s2039K ctx
dense
Falcon3 1B Instruct abliterated
D39
1B3.6 GB14 tok/s2251K ctx
dense
SmolVLM 500M Instruct
D38
0.5B3.4 GB7 tok/s2670K ctx
dense
👁 Unsloth
Qwen3.5 27B
D37
27B22.5 GB10 tok/s4K ctx
dense
👁 Unsloth
gemma 3 27b it
D37
27B22.5 GB10 tok/s4K ctx
dense
gemma 3 27b it
D37
27B22.5 GB10 tok/s4K ctx
dense
embeddinggemma 300M
D36
0.3B3.2 GB4 tok/s2697K ctx
dense
granite embedding 107m multilingual
D34
0.11B3.1 GB2 tok/s2726K ctx
dense
Falcon H1 Tiny 90M Instruct
D34
0.09B3.1 GB2 tok/s2727K ctx
dense
👁 Stability AI
StableLM 2 12B
D32
12B23.7 GB16 tok/s4K ctx
dense
👁 Meta
Llama 3.1 70B
F0
70B50.5 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.3 70B
F0
70B50.5 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 32B
F0
32B26.3 GB7 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 72B
F0
72B51.7 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 32B
F0
32B26.3 GB7 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 32B
F0
32B26.3 GB7 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
F0
235B149.1 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder-Next
F0
80B53.2 GB3 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B298.6 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 35B A3B
F0
35B25.7 GB17 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.6 35B A3B
F0
35B28.4 GB13 tok/s4K ctx
+1moe
👁 Alibaba
Qwen 3.5 122B A10B
F0
122B79.8 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B247.9 GB2 tok/s4K ctx
moe
👁 Google
Gemma 2 27B
F0
27B30.6 GB4 tok/s4K ctx
dense
👁 Google
Gemma 3 27B
F0
27B30.6 GB4 tok/s4K ctx
dense
👁 Mistral
Mixtral 8x7B
F0
47B33.5 GB5 tok/s4K ctx
moe
👁 Mistral
Mixtral 8x22B
F0
141B92.3 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 Distill 32B
F0
32B26.3 GB7 tok/s4K ctx
dense
👁 IBM
Granite 4.1 30B
F0
30B25.1 GB8 tok/s4K ctx
dense
👁 Cohere
Command R 35B
F0
35B26.7 GB6 tok/s4K ctx
dense
👁 TII
Falcon 40B Instruct
F0
40B33.5 GB3 tok/s4K ctx
dense
👁 BigCode
StarCoder 15B
F0
15B28.3 GB10 tok/s7K ctx
dense
👁 MosaicML
MPT-30B-Instruct
F0
30B47.9 GB2 tok/s4K ctx
dense
👁 Mistral
Devstral 2 123B Instruct
F0
123B83.3 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 4 119B
F0
119B80.9 GB2 tok/s4K ctx
moe
👁 Mistral
Leanstral 119B A6B
F0
119B84.3 GB2 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B420.0 GB2 tok/s4K ctx
+1moe
F0
744B475.8 GB2 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B481.9 GB2 tok/s4K ctx
moe
F0
1000B620.3 GB2 tok/s4K ctx
moe
F0
1000B620.3 GB2 tok/s4K ctx
+1moe
👁 Moonshot AI
Kimi Linear 48B A3B
F0
48B33.1 GB3 tok/s4K ctx
linear
👁 Nous Research
Nous Dolphin 13B
F0
13B24.5 GB15 tok/s10K ctx
dense
👁 Baichuan
Baichuan 13B
F0
13B24.5 GB15 tok/s8K ctx
dense
👁 InternLM
InternLM 20B
F0
20B35.6 GB4 tok/s4K ctx
dense
👁 01.AI
Yi 34B Chat
F0
34B27.3 GB6 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3 671B
F0
671B471.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B471.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B866.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Flash
F0
284B162.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B471.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B205.5 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B205.5 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek LLM 67B
F0
67B49.6 GB2 tok/s4K ctx
dense
👁 Meta
Llama 4 Scout 17B 16E
F0
109B72.3 GB2 tok/s4K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B249.8 GB2 tok/s4K ctx
moe
👁 Cohere
Command R+ 104B
F0
104B69.8 GB2 tok/s4K ctx
dense
👁 Cohere
Command A 111B
F0
111B74.5 GB2 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 34B
F0
34B27.3 GB6 tok/s4K ctx
dense
👁 Mistral AI
Pixtral Large 124B
F0
124B83.9 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 VL 72B
F0
72B51.7 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
F0
72B51.7 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 70B
F0
70B50.5 GB2 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 32B
F0
32B26.3 GB7 tok/s4K ctx
dense
👁 LG AI
EXAONE 4.0 32B
F0
32B26.3 GB7 tok/s4K ctx
dense
👁 Meta
Llama 3.1 405B
F0
405B257.6 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
F0
70B50.5 GB2 tok/s4K ctx
dense
👁 IBM
Granite Code 34B
F0
34B27.3 GB6 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 120B
F0
117B79.2 GB2 tok/s4K ctx
dense
👁 Cohere
Aya Expanse 32B
F0
32B24.9 GB7 tok/s4K ctx
dense
👁 Google
Gemma 4 31B
F0
30.7B36.3 GB3 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B412.7 GB2 tok/s4K ctx
moe
👁 NVIDIA
Nemotron Cascade 2 30B A3B
F0
30B24.1 GB22 tok/s4K ctx
moe
MiniMax M2.7
F0
230B147.0 GB2 tok/s4K ctx
moe
Solar Open 100B
F0
100B75.6 GB2 tok/s4K ctx
dense
Baichuan M2 32B Q4 K M
F0
32B26.2 GB6 tok/s4K ctx
dense
baichuan inc Baichuan M2 32B
F0
32B26.2 GB6 tok/s4K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
F0
48B37.8 GB2 tok/s4K ctx
dense
EXAONE 4.0 32B
F0
32B26.2 GB6 tok/s4K ctx
dense
K EXAONE 236B A23B
F0
236B174.5 GB2 tok/s4K ctx
dense
Qwen3.5 35B A3B
F0
35B28.4 GB5 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F0
70B53.8 GB2 tok/s4K ctx
dense
aya expanse 32b heretic MPOA i1
F0
32B26.2 GB6 tok/s4K ctx
dense
Baichuan M3 235B
F0
235B173.8 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0
235B173.8 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F0
72B55.3 GB2 tok/s4K ctx
dense
Solar Open 100B i1
F0
100B75.6 GB2 tok/s4K ctx
dense
Solar Open 69B REAP i1
F0
69B53.1 GB2 tok/s4K ctx
dense
Hermes 4.3 36B
F0
36B29.1 GB4 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F0
70B53.8 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
F0
122B77.0 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
F0
35B28.4 GB5 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 397B A17B
F0
397B291.6 GB2 tok/s4K ctx
dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

RX 7900 XT 20GB

20 GB VRAM

View tier list

RTX A4500 20GB

20 GB VRAM

View tier list

RTX 3090 24GB

24 GB VRAM

View tier list

RTX 3090 Ti 24GB

24 GB VRAM

View tier list
Full RTX 4000 Ada 20GB pageCompare this hardware