VOOZH about

URL: https://willitrunai.com/my-results/a100-40gb

⇱ NVIDIA A100 40GB AI Tier List: 309 models ranked | WillItRunAI


AI Compatibility Tier List

NVIDIA A100 40GB

374 AI models ranked by how well they run on your 40 GB VRAM hardware. Best match: Qwen 3.6 35B A3B (score: 99).

374

Models tested

309

Can run

40 GB

VRAM

166

Best tok/s

Tier Distribution

S 32
A 49
B 53
C 175
F 65
S: 32A: 49B: 53C: 175F: 65
S

S Tier -- Perfect Fit (32 models)

These models run flawlessly with headroom to spare.

👁 Alibaba
Qwen 3.6 35B A3B
S99
35B30.4 GB166 tok/s54K ctx
+1moe
👁 Alibaba
Qwen3-Coder 30B A3B Instruct
S98
30.5B25.0 GB198 tok/s180K ctx
moe
👁 Alibaba
Qwen 3.5 35B A3B
S98
35B27.7 GB181 tok/s131K ctx
moe
👁 Alibaba
Qwen 3.5 27B
S97
27B24.5 GB86 tok/s94K ctx
dense
👁 Alibaba
Qwen3-VL 30B A3B Instruct
S97
30B24.7 GB204 tok/s184K ctx
moe
👁 Alibaba
Qwen 3 32B
S97
32B28.3 GB73 tok/s64K ctx
dense
👁 Alibaba
Qwen 3 30B A3B
S96
30.5B25.0 GB198 tok/s131K ctx
moe
👁 NVIDIA
Nemotron 3 Nano 30B
S95
30B25.6 GB77 tok/s110K ctx
dense
👁 Mistral
Magistral Small 2507
S95
24B22.0 GB96 tok/s131K ctx
dense
👁 Mistral
Devstral Small 2 24B Instruct
S95
24B22.0 GB96 tok/s134K ctx
dense
👁 Alibaba
Qwen 3.6 27B
S95
27B22.3 GB53 tok/s262K ctx
+1dense
👁 NVIDIA
Nemotron Cascade 2 30B A3B
S94
30B26.1 GB202 tok/s92K ctx
moe
👁 Mistral
Devstral Small 1.1
S93
24B22.0 GB96 tok/s131K ctx
dense
👁 OpenAI
GPT-OSS 20B
S91
21B20.2 GB251 tok/s128K ctx
moe
👁 LG AI
EXAONE 4.0 32B
S91
32B28.3 GB72 tok/s64K ctx
dense
👁 Alibaba
Qwen 3 14B
S91
14B15.9 GB165 tok/s131K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
S91
14.7B16.9 GB157 tok/s33K ctx
dense
👁 Alibaba
Qwen 3.5 9B
S90
9B12.6 GB126 tok/s131K ctx
dense
👁 Google
Gemma 4 26B A4B
S90
25.2B23.9 GB212 tok/s86K ctx
moe
👁 Alibaba
Qwen 2.5 32B
S90
32B28.3 GB72 tok/s64K ctx
dense
👁 Allen AI
OLMo 2 32B
S88
32B28.3 GB72 tok/s4K ctx
dense
👁 Google
Gemma 4 31B
S88
30.7B38.3 GB46 tok/s18K ctx
dense
👁 Alibaba
Qwen 3 8B
S88
8B12.0 GB112 tok/s131K ctx
dense
👁 IBM
Granite 4.1 30B
S88
30B27.1 GB77 tok/s69K ctx
dense
👁 Mistral
Mistral Small 3.2 24B
S88
24B22.0 GB96 tok/s131K ctx
vision
👁 Google
Gemma 3 27B
S88
27B32.6 GB52 tok/s27K ctx
dense
👁 Mistral
Codestral 2 25.08
S87
22B20.8 GB93 tok/s142K ctx
dense
S87
24B22.0 GB96 tok/s131K ctx
dense
👁 Mistral
Mistral Small 24B
S86
24B22.0 GB96 tok/s33K ctx
dense
👁 Alibaba
Qwen 3.5 4B
S85
4B9.5 GB56 tok/s131K ctx
dense
👁 Mistral
Ministral 3 14B
S85
14B15.9 GB164 tok/s174K ctx
multimodal
S85
19B18.9 GB121 tok/s8K ctx
dense
A

A Tier -- Great Fit (49 models)

Excellent performance with comfortable memory margins.

👁 Mistral AI
Mistral Small 3.1 24B
A85
24B22.0 GB96 tok/s131K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 32B
A84
32B28.3 GB72 tok/s64K ctx
dense
👁 Moonshot AI
Kimi Linear 48B A3B
A84
48B35.1 GB45 tok/s100K ctx
linear
👁 NVIDIA
Nemotron Nano 8B
A83
8B11.7 GB112 tok/s131K ctx
dense
👁 IBM
Granite Code 34B
A83
34B29.3 GB68 tok/s8K ctx
dense
👁 IBM
Granite Code 20B
A82
20B20.3 GB116 tok/s8K ctx
dense
A82
14B16.5 GB164 tok/s16K ctx
dense
👁 Cohere
Command R 35B
A82
35B28.7 GB67 tok/s90K ctx
dense
👁 BigCode
StarCoder 15B
A82
15B30.3 GB123 tok/s8K ctx
dense
👁 Microsoft
Phi-4 Mini Reasoning 4B
A82
3.8B8.7 GB53 tok/s131K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 32B
A81
32B28.3 GB72 tok/s33K ctx
dense
👁 Alibaba
Qwen 2.5 14B
A81
14B16.4 GB165 tok/s131K ctx
dense
👁 Google
Gemma 3 12B
A81
12B17.1 GB116 tok/s91K ctx
dense
👁 InternLM
InternVL2 8B
A80
8B11.7 GB112 tok/s8K ctx
dense
👁 Meta
CodeLlama 13B Instruct
A80
13B25.0 GB165 tok/s16K ctx
dense
👁 DeepSeek
DeepSeek Coder V2 16B
A80
16B18.0 GB319 tok/s123K ctx
moe
👁 Mistral
Ministral 3 8B
A79
8B12.0 GB112 tok/s220K ctx
multimodal
👁 OpenBMB
MiniCPM-V 2.6 8B
A79
8B11.7 GB112 tok/s2K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
A79
13B25.0 GB165 tok/s4K ctx
dense
👁 NVIDIA
Nemotron Nano 9B v2
A78
9B12.8 GB126 tok/s131K ctx
dense
👁 Defog
SQLCoder 7B
A77
7B11.1 GB98 tok/s8K ctx
dense
👁 AllenAI
OLMo 2 13B
A77
13B15.3 GB178 tok/s33K ctx
dense
👁 Alibaba
Qwen 2.5 VL 7B
A77
7B10.0 GB98 tok/s33K ctx
dense
👁 Alibaba
Qwen 3 4B
A77
4B9.5 GB56 tok/s33K ctx
dense
👁 Nous Research
Nous Dolphin 13B
A77
13B26.5 GB142 tok/s16K ctx
dense
👁 WizardLM
WizardLM 13B
A76
13B25.0 GB165 tok/s8K ctx
dense
👁 LMSYS
Vicuna 13B
A76
13B25.0 GB165 tok/s4K ctx
dense
👁 Magistral AI
Magistral 7B
A76
7B11.1 GB98 tok/s8K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
A76
9B11.0 GB126 tok/s131K ctx
dense
👁 Jina AI
Jina Embeddings v3
A75
0.57B8.0 GB8 tok/s8K ctx
dense
👁 Google
Gemma 4 E4B
A75
8B11.1 GB112 tok/s128K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 14B
A75
14B16.4 GB165 tok/s33K ctx
dense
👁 Google
Gemma 2 27B
A75
27B32.6 GB52 tok/s8K ctx
dense
👁 Nous Research
Nous Hermes 1.0
A75
9B22.6 GB126 tok/s16K ctx
dense
👁 Meta
CodeLlama 7B Instruct
A74
7B17.0 GB98 tok/s16K ctx
dense
👁 BigCode
StarCoder 7B
A74
7B16.5 GB98 tok/s8K ctx
dense
👁 BAAI
BGE M3
A74
0.57B7.2 GB8 tok/s8K ctx
dense
👁 Mistral AI
Pixtral 12B
A73
12B14.7 GB168 tok/s131K ctx
dense
👁 IBM
Granite Code 8B
A73
8B11.7 GB112 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 7B
A73
7B10.0 GB98 tok/s131K ctx
dense
👁 DevStral AI
DevStral 7B
A73
7B11.1 GB98 tok/s8K ctx
dense
👁 IBM
Granite 4.1 8B
A73
8B12.2 GB112 tok/s131K ctx
dense
👁 TII
Falcon 40B Instruct
A73
40B35.5 GB50 tok/s8K ctx
dense
👁 Baichuan
Baichuan 13B
A72
13B26.5 GB142 tok/s8K ctx
dense
👁 Mistral AI
Codestral Mamba 7B
A72
7B9.7 GB98 tok/s262K ctx
state-space
👁 InternLM
InternLM 7B
A72
7B17.0 GB98 tok/s8K ctx
dense
👁 InternLM
InternLM Chat 7B
A72
7B17.0 GB98 tok/s8K ctx
dense
👁 Cerebras
Cerebras-GPT 13B
A71
13B24.0 GB142 tok/s42K ctx
dense
👁 Mixedbread AI
mxbai Embed Large
A71
0.34B7.1 GB5 tok/s1K ctx
dense
B

B Tier -- Good Fit (53 models)

Solid performance, may need quantization or reduced context.

👁 Alibaba
Qwen 2.5 Coder 3B
B70
3B8.9 GB42 tok/s131K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
B70
0.34B7.1 GB5 tok/s1K ctx
dense
👁 Mistral
Mixtral 8x7B
B69
47B35.5 GB94 tok/s33K ctx
moe
👁 Meta
Llama 3.1 8B
B69
8B11.7 GB112 tok/s128K ctx
dense
👁 Zhipu
GLM-4 9B
B69
9B11.0 GB126 tok/s128K ctx
dense
B69
7B12.1 GB98 tok/s8K ctx
dense
👁 LLaVA
LLaVA 1.5 7B
B69
7B17.0 GB98 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 34B
B69
34B29.3 GB68 tok/s4K ctx
dense
👁 Google
Gemma 4 E2B
B69
5.1B8.5 GB71 tok/s128K ctx
dense
👁 WizardLM
WizardMath 7B
B68
7B11.1 GB98 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
B68
7B11.1 GB98 tok/s4K ctx
dense
👁 BAAI
BGE Large EN v1.5
B68
0.34B7.1 GB5 tok/s1K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 7B
B67
7B10.0 GB98 tok/s131K ctx
dense
👁 MosaicML
MPT-7B-Instruct
B67
7B17.0 GB98 tok/s8K ctx
dense
👁 Baichuan
Baichuan 7B
B67
7B17.0 GB98 tok/s8K ctx
dense
👁 Google
Gemma 3 4B
B67
4B9.4 GB56 tok/s128K ctx
dense
👁 Nomic AI
Nomic Embed Text v1.5
B66
0.14B5.7 GB2 tok/s8K ctx
dense
👁 Mistral
Ministral 3 3B
B66
3B7.5 GB42 tok/s262K ctx
multimodal
👁 Microsoft
Phi 4 Mini 4B
B66
4B8.8 GB56 tok/s128K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 14B
B65
14B16.4 GB165 tok/s131K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 8B
B65
8B11.7 GB112 tok/s33K ctx
dense
👁 Google
Gemma 2 9B
B65
9B15.5 GB126 tok/s8K ctx
dense
👁 Alibaba
Qwen 3.5 2B
B64
2B7.8 GB28 tok/s131K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 7B
B64
7B10.0 GB98 tok/s33K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
B64
3.8B13.1 GB53 tok/s90K ctx
dense
7B11.1 GB98 tok/s4K ctx
dense
👁 Meta
Llama 3.2 11B Vision
B64
11B13.6 GB154 tok/s16K ctx
vision
👁 Mistral AI
Codestral 22B
B63
22B20.8 GB99 tok/s33K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
B63
4B13.2 GB56 tok/s89K ctx
dense
👁 TII
Falcon 7B Instruct
B63
7B9.3 GB98 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 3B
B63
3B8.9 GB42 tok/s131K ctx
dense
👁 Mistral
Mistral Nemo 12B
B62
12B14.7 GB168 tok/s128K ctx
dense
👁 InternLM
InternLM 20B
B62
20B37.6 GB93 tok/s8K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
B62
14B16.5 GB164 tok/s128K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B61
1.7B7.6 GB24 tok/s33K ctx
dense
👁 Cohere
Aya Expanse 32B
B61
32B26.9 GB73 tok/s8K ctx
dense
👁 IBM
Granite 4.1 3B
B61
3B8.0 GB42 tok/s131K ctx
dense
👁 01.AI
Yi Coder 9B
B60
9B11.9 GB126 tok/s131K ctx
dense
👁 IBM
Granite Code 3B
B60
3B9.2 GB42 tok/s8K ctx
dense
B60
0.02B5.2 GB2 tok/s0K ctx
dense
👁 Mistral
Mistral 7B Instruct v0.3
B60
7B11.1 GB98 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 1.5B
B59
1.5B6.2 GB21 tok/s33K ctx
dense
👁 Mistral
Ministral 8B
B58
8B12.0 GB112 tok/s131K ctx
dense
👁 01.AI
Yi 34B Chat
B57
34B29.3 GB68 tok/s63K ctx
dense
👁 Meta
Llama 3.2 3B
B56
3B8.4 GB42 tok/s128K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
B56
35B30.4 GB61 tok/s54K ctx
dense
Qwen3.5 35B A3B
B56
35B30.4 GB61 tok/s54K ctx
dense
EXAONE 4.0 32B
B56
32B28.2 GB67 tok/s66K ctx
dense
aya expanse 32b heretic MPOA i1
B56
32B28.2 GB67 tok/s66K ctx
dense
Baichuan M2 32B Q4 K M
B56
32B28.2 GB67 tok/s66K ctx
dense
baichuan inc Baichuan M2 32B
B55
32B28.2 GB67 tok/s66K ctx
dense
👁 Stability AI
StableLM 2 12B
B55
12B25.7 GB116 tok/s4K ctx
dense
Hermes 4.3 36B
B55
36B31.1 GB60 tok/s50K ctx
dense
C

C Tier -- Tight Fit (175 models)

Runs with offloading or significant compromises.

👁 Unsloth
Qwen3.5 27B
C55
27B24.5 GB79 tok/s94K ctx
dense
👁 Unsloth
gemma 3 27b it
C55
27B24.5 GB79 tok/s94K ctx
dense
gemma 3 27b it
C55
27B24.5 GB79 tok/s94K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
C54
24B22.4 GB89 tok/s116K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C54
24B22.4 GB89 tok/s116K ctx
dense
Mistral Small 24B Instruct 2501
C54
24B22.4 GB89 tok/s116K ctx
dense
mistral small 3.1 24b instruct 2503 hf
C54
24B22.4 GB89 tok/s116K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
C54
24B22.4 GB89 tok/s116K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
C54
24B22.4 GB89 tok/s116K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C53
24B22.4 GB89 tok/s116K ctx
dense
Codestral 22B v0.1
C53
22B20.9 GB97 tok/s135K ctx
dense
Codestral 22B v0.1
C53
22B20.9 GB97 tok/s135K ctx
dense
Codestral 22B v0.1
C53
22B20.9 GB97 tok/s135K ctx
dense
👁 IBM
Granite 3.1 8B
C53
8B11.7 GB112 tok/s128K ctx
state-space
👁 01.AI
Yi 1.5 9B
C53
9B11.9 GB126 tok/s4K ctx
dense
Codestral 22B v0.1 IMat
C53
22B20.9 GB97 tok/s135K ctx
dense
Codestral 22B v0.1 i1
C53
22B20.9 GB97 tok/s135K ctx
dense
👁 BigCode
StarCoder2 15B
C52
15B16.9 GB135 tok/s16K ctx
dense
Codestral 21B Pruned i1
C52
21B20.2 GB102 tok/s145K ctx
dense
internlm2 5 20b chat
C52
20B19.4 GB107 tok/s156K ctx
dense
internlm2 limarp chat 20b
C52
20B19.4 GB107 tok/s156K ctx
dense
C52
3B8.7 GB42 tok/s128K ctx
dense
internlm2 math plus 20b i1
C52
20B19.4 GB107 tok/s156K ctx
dense
👁 LMSYS
Vicuna 7B
C52
7B17.0 GB98 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
C51
7B10.0 GB98 tok/s4K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
C51
48B39.8 GB45 tok/s17K ctx
dense
Codestral RAG 19B Pruned i1
C51
19B18.7 GB113 tok/s169K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
C51
1.5B6.2 GB21 tok/s33K ctx
dense
👁 TinyLlama
TinyLlama 1.1B
C51
1.1B5.9 GB15 tok/s4K ctx
dense
Phi 4 reasoning vision 15B
C50
15B15.8 GB143 tok/s236K ctx
dense
StarCoder2 15B
C50
15B15.8 GB143 tok/s236K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
C50
14B15.1 GB153 tok/s259K ctx
dense
starcoder2 15b instruct v0.1
C50
15B15.8 GB143 tok/s236K ctx
dense
starcoder2 15b i1
C50
15B15.8 GB143 tok/s236K ctx
dense
starcoder2 15b instruct v0.1
C50
15B15.8 GB143 tok/s236K ctx
dense
HelpingAI 15B i1
C50
15B15.8 GB143 tok/s236K ctx
dense
NousResearch Hermes 4 14B
C50
14B15.1 GB153 tok/s259K ctx
dense
👁 OpenChat
OpenChat 7B
C50
7B11.1 GB98 tok/s8K ctx
dense
👁 Cohere
Aya Expanse 8B
C50
8B11.7 GB112 tok/s8K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
C50
14B15.1 GB153 tok/s259K ctx
dense
internlm JanusCoder 14B
C50
14B15.1 GB153 tok/s259K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
C50
14B15.1 GB153 tok/s259K ctx
dense
gemma 3 12b it
C49
12B13.6 GB168 tok/s316K ctx
dense
👁 DeepSeek
DeepSeek LLM 7B
C49
7B16.5 GB98 tok/s4K ctx
dense
8B11.7 GB112 tok/s33K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C49
10.7B12.7 GB150 tok/s365K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
C49
1.5B6.2 GB21 tok/s131K ctx
dense
👁 Teknium
OpenHermes 2.5 7B
C49
7B11.1 GB98 tok/s8K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C49
10.7B12.7 GB150 tok/s365K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
C48
7B11.1 GB98 tok/s33K ctx
dense
👁 Unsloth
Qwen3.5 9B
C48
9B11.4 GB126 tok/s449K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C48
9B11.4 GB126 tok/s449K ctx
dense
solar finalised finetuned Model 10.7B i1
C48
10.7B12.7 GB150 tok/s365K ctx
dense
SOLAR 10.7B v1.0
C48
10.7B12.7 GB150 tok/s365K ctx
dense
Qwen3.5 9B
C48
9B11.4 GB126 tok/s449K ctx
dense
👁 UC Berkeley
Starling LM 7B
C48
7B11.1 GB98 tok/s8K ctx
dense
Yi Coder 9B Chat
C48
9B11.4 GB126 tok/s449K ctx
dense
glm 4 9b chat 1m
C48
9B11.4 GB126 tok/s449K ctx
dense
Meta Llama 3.1 8B Instruct
C48
8B10.7 GB112 tok/s516K ctx
dense
Helply 10.2b chat i1
C48
10.2B12.3 GB143 tok/s387K ctx
dense
llava llama 3 8b v1 1
C48
8B10.7 GB112 tok/s516K ctx
dense
HelpingAI2.5 10B i1
C48
10B12.2 GB140 tok/s396K ctx
dense
Yi 1.5 9B Chat
C48
9B11.4 GB126 tok/s449K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
C48
8B10.7 GB112 tok/s516K ctx
dense
Meta Llama 3 8B Instruct
C48
8B10.7 GB112 tok/s516K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
C48
8B10.7 GB112 tok/s516K ctx
dense
Dolphin3.0 Llama3.1 8B
C48
8B10.7 GB112 tok/s516K ctx
dense
Llama 3 8B Instruct 32k v0.1
C48
8B10.7 GB112 tok/s516K ctx
dense
Meta Llama 3.1 8B Instruct
C48
8B10.7 GB112 tok/s516K ctx
dense
vntl llama3 8b v2
C48
8B10.7 GB112 tok/s516K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C48
8B10.7 GB112 tok/s516K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C48
8B10.7 GB112 tok/s516K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C48
8B10.7 GB112 tok/s516K ctx
dense
Yi 9B Coder i1
C48
9B11.4 GB126 tok/s449K ctx
dense
Hermes 3 Llama 3.1 8B
C48
8B10.7 GB112 tok/s516K ctx
dense
HelpingAI2 9B
C48
9B11.4 GB126 tok/s449K ctx
dense
Llama 2 7B Chat
C48
7B10.0 GB98 tok/s601K ctx
dense
Hermes 2 Pro Llama 3 8B
C48
8B10.7 GB112 tok/s516K ctx
dense
Dolphin3.0 Llama3.1 8B
C48
8B10.7 GB112 tok/s516K ctx
dense
granite 8b code instruct 4k
C48
8B10.7 GB112 tok/s516K ctx
dense
dolphin 2.9.4 llama3.1 8b
C47
8B10.7 GB112 tok/s516K ctx
dense
HelpingAI2 9B i1
C47
9B11.4 GB126 tok/s449K ctx
dense
Mistral 7B Instruct v0.2
C47
7B10.0 GB98 tok/s601K ctx
dense
HelpingAI 9B 200k i1
C47
9B11.4 GB126 tok/s449K ctx
dense
Mistral 7B Instruct v0.3
C47
7B10.0 GB98 tok/s601K ctx
dense
HelpingAI 9B i1
C47
9B11.4 GB126 tok/s449K ctx
dense
openchat 3.6 8b 20240522 IMat
C47
8B10.7 GB112 tok/s516K ctx
dense
aya expanse 8b
C47
8B10.7 GB112 tok/s516K ctx
dense
dolphin v2 8b abliterated i1
C47
8B10.7 GB112 tok/s516K ctx
dense
EXAONE 3.5 7.8B Instruct
C47
7.8B10.6 GB109 tok/s531K ctx
dense
EXAONE 3.5 7.8B Instruct
C47
7.8B10.6 GB109 tok/s531K ctx
dense
aya expanse 8b orthogonal heretic i1
C47
8B10.7 GB112 tok/s516K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C47
7.8B10.6 GB109 tok/s531K ctx
dense
exaone 3.0 7.8b it
C47
7.8B10.6 GB109 tok/s531K ctx
dense
Mistral 7B Instruct v0.3
C47
7B10.0 GB98 tok/s601K ctx
dense
Hermes 2 Pro Mistral 7B
C47
7B10.0 GB98 tok/s601K ctx
dense
aya expanse 8b orthogonal heretic
C47
8B10.7 GB112 tok/s516K ctx
dense
zephyr 7B beta
C47
7B10.0 GB98 tok/s601K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C47
7B10.0 GB98 tok/s601K ctx
dense
Falcon H1R 7B
C47
7B10.0 GB98 tok/s601K ctx
dense
internlm2 5 1 8b chat i1
C47
8B10.7 GB112 tok/s516K ctx
dense
internlm3 8b instruct abliterated i1
C47
8B10.7 GB112 tok/s516K ctx
dense
falcon mamba 7b instruct Q4 K M
C47
7B10.0 GB98 tok/s601K ctx
dense
👁 Intel
Neural Chat 7B
C47
7B11.1 GB98 tok/s8K ctx
dense
zephyr 7B alpha
C47
7B10.0 GB98 tok/s601K ctx
dense
speechless zephyr code functionary 7b
C47
7B10.0 GB98 tok/s601K ctx
dense
StarCoder2 7B
C47
7B10.0 GB98 tok/s601K ctx
dense
👁 Google
Gemma 3 1B
C47
1B5.9 GB14 tok/s33K ctx
dense
japanese stablelm instruct gamma 7B
C47
7B10.0 GB98 tok/s601K ctx
dense
Falcon H1 7B Instruct
C47
7B10.0 GB98 tok/s601K ctx
dense
👁 Unsloth
Falcon H1R 7B
C47
7B10.0 GB98 tok/s601K ctx
dense
👁 Google
Gemma 2 2B
C47
2B7.7 GB28 tok/s8K ctx
dense
Mamba Codestral 7B v0.1
C47
7B10.0 GB98 tok/s601K ctx
dense
stabilityai japanese stablelm base gamma 7b
C47
7B10.0 GB98 tok/s601K ctx
dense
baichuan2 7b chat
C47
7B10.0 GB98 tok/s601K ctx
dense
DiscoPOP zephyr 7b gemma
C47
7B10.0 GB98 tok/s601K ctx
dense
starcoder2 7b
C47
7B10.0 GB98 tok/s601K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C47
7B10.0 GB98 tok/s601K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C47
7B10.0 GB98 tok/s601K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C47
7B10.0 GB98 tok/s601K ctx
dense
internlm2 math plus 7b IMat
C47
7B10.0 GB98 tok/s601K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C47
7B10.0 GB98 tok/s601K ctx
dense
internlm2 5 7b chat i1
C47
7B10.0 GB98 tok/s601K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C47
7B10.0 GB98 tok/s601K ctx
dense
MD Judge v0 2 internlm2 7b i1
C47
7B10.0 GB98 tok/s601K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C47
7B10.0 GB98 tok/s601K ctx
dense
jointpreferences mistral 7b sft helpful
C47
7B10.0 GB98 tok/s601K ctx
dense
zephyr 7b dpo full i1
C47
7B10.0 GB98 tok/s601K ctx
dense
blossom v3 baichuan2 7b i1
C47
7B10.0 GB98 tok/s601K ctx
dense
blossom v1 baichuan 7b i1
C47
7B10.0 GB98 tok/s601K ctx
dense
Yi 1.5 6B Chat
C47
6B9.3 GB84 tok/s715K ctx
dense
stablelm 2 zephyr 1 6b
C47
6B9.3 GB84 tok/s715K ctx
dense
👁 01.AI
Yi 1.5 6B
C46
6B9.5 GB84 tok/s4K ctx
dense
Yi 1.5 6B Chat
C46
6B9.3 GB84 tok/s715K ctx
dense
stablelm 2 1 6b chat imatrix
C46
6B9.3 GB84 tok/s715K ctx
dense
👁 BigCode
StarCoder2 7B
C46
7B9.7 GB98 tok/s16K ctx
dense
HelpingAI2 6B
C46
6B9.3 GB84 tok/s715K ctx
dense
HelpingAI2 6B i1
C46
6B9.3 GB84 tok/s715K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
C46
4B9.3 GB56 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C46
0.5B5.4 GB7 tok/s131K ctx
dense
HelpingAI2.5 5B i1
C45
5B8.5 GB70 tok/s875K ctx
dense
👁 Unsloth
Qwen3.5 4B
C45
4B7.8 GB56 tok/s1115K ctx
dense
gemma 3 4b it
C45
4B7.8 GB56 tok/s1115K ctx
dense
gemma 3 4b it
C45
4B7.8 GB56 tok/s1115K ctx
dense
👁 Alibaba
Qwen 3 0.6B
C44
0.6B6.1 GB8 tok/s33K ctx
dense
👁 Meta
Llama 3.2 1B
C44
1B6.0 GB14 tok/s128K ctx
dense
Llama 3.2 3B Instruct
C44
3B7.4 GB42 tok/s1499K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C43
3B7.1 GB42 tok/s1514K ctx
dense
Llama 3.2 3B Instruct
C43
3B7.1 GB42 tok/s1514K ctx
dense
Ministral 3 3B Instruct 2512
C43
3B7.1 GB42 tok/s1514K ctx
dense
HELVETE 3B
C43
3B7.1 GB42 tok/s1514K ctx
dense
Hermes 3 Llama 3.2 3B
C43
3B7.1 GB42 tok/s1514K ctx
dense
stablelm zephyr 3b
C43
3B7.1 GB42 tok/s1514K ctx
dense
StarCoder2 3B
C43
3B7.1 GB42 tok/s1514K ctx
dense
AI21 Jamba Reasoning 3B
C43
3B7.1 GB42 tok/s1514K ctx
dense
stablelm 3b 4e1t
C43
3B7.1 GB42 tok/s1514K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C43
3B7.1 GB42 tok/s1514K ctx
dense
ai21labs AI21 Jamba2 3B
C43
3B7.1 GB42 tok/s1514K ctx
dense
HelpingAI 3B hindi i1
C43
3B7.1 GB42 tok/s1514K ctx
dense
AI21 Jamba2 3B
C43
3B7.1 GB42 tok/s1514K ctx
dense
HelpingAI 3B hindi
C43
3B7.1 GB42 tok/s1514K ctx
dense
AI21 Jamba2 3B i1
C43
3B7.1 GB42 tok/s1514K ctx
dense
gemma 2 2b it
C42
2B6.8 GB28 tok/s2284K ctx
dense
EXAONE 3.5 2.4B Instruct
C42
2.4B6.6 GB34 tok/s1914K ctx
dense
👁 Google
gemma 2b
C42
2B6.4 GB28 tok/s2313K ctx
dense
👁 BigCode
StarCoder2 3B
C42
3B7.2 GB42 tok/s16K ctx
dense
Gemmasutra Mini 2B v1
C42
2B6.4 GB28 tok/s2313K ctx
dense
gemma 2 2b it
C42
2B6.4 GB28 tok/s2313K ctx
dense
👁 Alibaba
Qwen 3.5 0.6B
C41
0.6B6.1 GB8 tok/s131K ctx
dense
👁 Qwen
Qwen2.5 1.5B Instruct
C41
1.5B6.0 GB21 tok/s3112K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B
C41
1.5B6.0 GB21 tok/s3112K ctx
dense
Yi Coder 1.5B Chat
C40
1.5B6.0 GB21 tok/s3112K ctx
dense
stablelm 2 zephyr 1.6b
C40
1.6B6.1 GB22 tok/s2912K ctx
dense
logos16v2 stablelm2 1.6b i1
C40
1.6B6.1 GB22 tok/s2912K ctx
dense
Yi Coder 1.5B
C40
1.5B6.0 GB21 tok/s3112K ctx
dense
F

F Tier -- Can't Run (65 models)

Too heavy for this hardware.

👁 Unsloth
Falcon H1 1.5B Instruct
D40
1.5B6.0 GB21 tok/s3112K ctx
dense
TinyLlama 1.1B Chat v1.0
D39
1.1B5.7 GB15 tok/s4273K ctx
dense
EXAONE 4.0 1.2B
D39
1.2B5.8 GB17 tok/s3910K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
D39
0.5B5.4 GB7 tok/s131K ctx
dense
Llama 3.2 1B Instruct Q8 0
D39
1B5.8 GB14 tok/s4680K ctx
dense
TinyLlama 1.1B Chat v0.3
D39
1.1B5.7 GB15 tok/s4273K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
D39
1.1B5.7 GB15 tok/s4273K ctx
dense
Llama 3.2 1B Instruct
D39
1B5.6 GB14 tok/s4709K ctx
dense
gemma 3 1b it
D39
1B5.6 GB14 tok/s4709K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
D39
1.1B5.7 GB15 tok/s4273K ctx
dense
Falcon3 1B Instruct abliterated
D39
1B5.6 GB14 tok/s4709K ctx
dense
SmolVLM 500M Instruct
D37
0.5B5.4 GB7 tok/s5550K ctx
dense
embeddinggemma 300M
D35
0.3B5.2 GB4 tok/s5577K ctx
dense
granite embedding 107m multilingual
D33
0.11B5.1 GB2 tok/s5606K ctx
dense
Falcon H1 Tiny 90M Instruct
D33
0.09B5.1 GB2 tok/s5607K ctx
dense
👁 Meta
Llama 3.1 70B
F0
70B52.5 GB14 tok/s4K ctx
dense
👁 Meta
Llama 3.3 70B
F0
70B52.5 GB14 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 72B
F0
72B53.7 GB13 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
F0
235B151.1 GB4 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder-Next
F0
80B55.2 GB34 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B300.6 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 122B A10B
F0
122B81.8 GB9 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B249.9 GB3 tok/s4K ctx
moe
👁 Mistral
Mixtral 8x22B
F0
141B94.3 GB5 tok/s4K ctx
moe
👁 MosaicML
MPT-30B-Instruct
F0
30B49.9 GB29 tok/s8K ctx
dense
👁 Mistral
Devstral 2 123B Instruct
F0
123B85.3 GB3 tok/s4K ctx
dense
👁 Mistral
Mistral Small 4 119B
F0
119B82.9 GB9 tok/s4K ctx
moe
👁 Mistral
Leanstral 119B A6B
F0
119B86.3 GB8 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B422.0 GB2 tok/s4K ctx
+1moe
F0
744B477.8 GB2 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B483.9 GB2 tok/s4K ctx
moe
F0
1000B622.3 GB2 tok/s4K ctx
moe
F0
1000B622.3 GB2 tok/s4K ctx
+1moe
👁 DeepSeek
DeepSeek V3 671B
F0
671B473.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B473.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B868.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Flash
F0
284B164.2 GB4 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B473.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B207.5 GB4 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B207.5 GB4 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek LLM 67B
F0
67B51.6 GB15 tok/s4K ctx
dense
👁 Meta
Llama 4 Scout 17B 16E
F0
109B74.3 GB10 tok/s4K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B251.8 GB3 tok/s4K ctx
moe
👁 Cohere
Command R+ 104B
F0
104B71.8 GB5 tok/s4K ctx
dense
👁 Cohere
Command A 111B
F0
111B76.5 GB4 tok/s4K ctx
dense
👁 Mistral AI
Pixtral Large 124B
F0
124B85.9 GB3 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 VL 72B
F0
72B53.7 GB13 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
F0
72B53.7 GB13 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 70B
F0
70B52.5 GB14 tok/s4K ctx
dense
👁 Meta
Llama 3.1 405B
F0
405B259.6 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
F0
70B52.5 GB14 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 120B
F0
117B81.2 GB3 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B414.7 GB2 tok/s4K ctx
moe
MiniMax M2.7
F0
230B149.0 GB5 tok/s4K ctx
moe
Solar Open 100B
F0
100B77.6 GB4 tok/s4K ctx
dense
K EXAONE 236B A23B
F0
236B176.5 GB2 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F0
70B55.8 GB11 tok/s4K ctx
dense
Baichuan M3 235B
F0
235B175.8 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0
235B175.8 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F0
72B57.3 GB11 tok/s4K ctx
dense
Solar Open 100B i1
F0
100B77.6 GB4 tok/s4K ctx
dense
Solar Open 69B REAP i1
F0
69B55.1 GB12 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F0
70B55.8 GB11 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
F0
122B79.0 GB4 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 397B A17B
F0
397B293.6 GB2 tok/s4K ctx
dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

RTX 5090 32GB

32 GB VRAM

View tier list

RTX 5000 Ada 32GB

32 GB VRAM

View tier list

RTX 6000 Ada 48GB

48 GB VRAM

View tier list

RTX PRO 4500 Blackwell 32GB

32 GB VRAM

View tier list
Full NVIDIA A100 40GB pageCompare this hardware