VOOZH about

URL: https://willitrunai.com/my-results/h200-pcie-141gb

⇱ NVIDIA H200 PCIe 141GB AI Tier List: 332 models ranked | WillItRunAI


AI Compatibility Tier List

NVIDIA H200 PCIe 141GB

374 AI models ranked by how well they run on your 141 GB VRAM hardware. Best match: Qwen 3.5 122B A10B (score: 98).

374

Models tested

332

Can run

141 GB

VRAM

162

Best tok/s

Tier Distribution

S 29
A 57
B 58
C 188
F 42
S: 29A: 57B: 58C: 188F: 42
S

S Tier -- Perfect Fit (29 models)

These models run flawlessly with headroom to spare.

👁 Alibaba
Qwen 3.5 122B A10B
S98
122B91.9 GB162 tok/s131K ctx
moe
👁 Mistral
Devstral 2 123B Instruct
S98
123B95.4 GB58 tok/s152K ctx
dense
👁 Mistral
Mistral Small 4 119B
S97
119B93.0 GB176 tok/s159K ctx
moe
👁 OpenAI
GPT-OSS 120B
S95
117B91.3 GB61 tok/s131K ctx
dense
👁 Mistral AI
Pixtral Large 124B
S95
124B96.0 GB58 tok/s131K ctx
dense
👁 Cohere
Command A 111B
S94
111B86.6 GB65 tok/s239K ctx
dense
👁 Mistral
Leanstral 119B A6B
S92
119B96.4 GB162 tok/s97K ctx
moe
👁 Alibaba
Qwen 2.5 VL 72B
S92
72B63.8 GB100 tok/s33K ctx
dense
👁 Alibaba
Qwen3-Coder-Next
S92
80B65.3 GB272 tok/s256K ctx
moe
👁 Alibaba
Qwen3-Coder 30B A3B Instruct
S90
30.5B35.1 GB610 tok/s256K ctx
moe
👁 Alibaba
Qwen 3.6 35B A3B
S90
35B40.5 GB512 tok/s262K ctx
+1moe
👁 Alibaba
Qwen 3.5 27B
S90
27B34.6 GB264 tok/s131K ctx
dense
👁 Alibaba
Qwen3-VL 30B A3B Instruct
S89
30B34.8 GB631 tok/s256K ctx
moe
👁 Alibaba
Qwen 3.6 27B
S89
27B32.4 GB165 tok/s262K ctx
+1dense
👁 Alibaba
Qwen 3.5 35B A3B
S89
35B37.8 GB557 tok/s131K ctx
moe
👁 Alibaba
Qwen 3 32B
S89
32B38.4 GB225 tok/s131K ctx
dense
👁 Mistral
Magistral Small 2507
S88
24B32.1 GB296 tok/s131K ctx
dense
👁 Mistral
Devstral Small 2 24B Instruct
S88
24B32.1 GB296 tok/s256K ctx
dense
👁 Alibaba
Qwen 3 30B A3B
S88
30.5B35.1 GB610 tok/s131K ctx
moe
👁 NVIDIA
Nemotron 3 Nano 30B
S87
30B35.7 GB237 tok/s131K ctx
dense
👁 Alibaba
Qwen 3.5 9B
S87
9B22.7 GB126 tok/s131K ctx
dense
👁 Alibaba
Qwen 3 14B
S87
14B26.0 GB196 tok/s131K ctx
dense
👁 Mistral
Devstral Small 1.1
S86
24B32.1 GB296 tok/s131K ctx
dense
👁 Google
Gemma 4 31B
S86
30.7B48.4 GB141 tok/s117K ctx
dense
👁 Meta
Llama 3.3 70B
S86
70B62.6 GB103 tok/s128K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
S86
14.7B27.0 GB206 tok/s33K ctx
dense
👁 Alibaba
Qwen 3 8B
S85
8B22.1 GB112 tok/s131K ctx
dense
👁 NVIDIA
Nemotron Cascade 2 30B A3B
S85
30B36.2 GB623 tok/s262K ctx
moe
👁 OpenAI
GPT-OSS 20B
S85
21B30.3 GB774 tok/s128K ctx
moe
A

A Tier -- Great Fit (57 models)

Excellent performance with comfortable memory margins.

👁 Alibaba
Qwen 3.5 4B
A83
4B19.6 GB56 tok/s131K ctx
dense
👁 LG AI
EXAONE 4.0 32B
A83
32B38.4 GB223 tok/s131K ctx
dense
👁 Alibaba
Qwen 2.5 72B
A83
72B63.8 GB100 tok/s131K ctx
dense
👁 Meta
Llama 4 Scout 17B 16E
A83
109B84.4 GB154 tok/s325K ctx
moe
👁 Meta
Llama 3.1 70B
A82
70B62.6 GB103 tok/s128K ctx
dense
👁 Google
Gemma 4 26B A4B
A82
25.2B34.0 GB655 tok/s256K ctx
moe
👁 Alibaba
Qwen 2.5 32B
A81
32B38.4 GB223 tok/s131K ctx
dense
👁 Moonshot AI
Kimi Linear 48B A3B
A81
48B45.2 GB138 tok/s1049K ctx
linear
👁 Google
Gemma 3 27B
A81
27B42.7 GB160 tok/s131K ctx
dense
👁 Mistral
Ministral 3 14B
A81
14B26.0 GB196 tok/s262K ctx
multimodal
👁 Mistral
Codestral 2 25.08
A81
22B30.9 GB288 tok/s256K ctx
dense
👁 Mistral
Mistral Small 3.2 24B
A81
24B32.1 GB296 tok/s131K ctx
vision
👁 NVIDIA
Nemotron Nano 8B
A80
8B21.8 GB112 tok/s131K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
A80
235B161.2 GB48 tok/s4K ctx
moe
👁 Microsoft
Phi-4 Mini Reasoning 4B
A80
3.8B18.8 GB53 tok/s131K ctx
dense
👁 Allen AI
OLMo 2 32B
A80
32B38.4 GB223 tok/s4K ctx
dense
A80
24B32.1 GB296 tok/s131K ctx
dense
👁 IBM
Granite 4.1 30B
A80
30B37.2 GB237 tok/s131K ctx
dense
A80
19B29.0 GB266 tok/s8K ctx
dense
👁 Mistral
Mistral Small 24B
A79
24B32.1 GB296 tok/s33K ctx
dense
MiniMax M2.7
A79
230B159.1 GB56 tok/s4K ctx
moe
👁 Mistral AI
Mistral Small 3.1 24B
A78
24B32.1 GB296 tok/s131K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
A78
70B62.6 GB103 tok/s131K ctx
dense
A78
14B26.6 GB196 tok/s16K ctx
dense
👁 InternLM
InternVL2 8B
A78
8B21.8 GB112 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 14B
A77
14B26.5 GB196 tok/s131K ctx
dense
👁 IBM
Granite Code 20B
A76
20B30.4 GB280 tok/s8K ctx
dense
👁 Mistral
Ministral 3 8B
A76
8B22.1 GB112 tok/s262K ctx
multimodal
👁 OpenBMB
MiniCPM-V 2.6 8B
A76
8B21.8 GB112 tok/s2K ctx
dense
👁 Google
Gemma 3 12B
A76
12B27.2 GB168 tok/s131K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 32B
A75
32B38.4 GB223 tok/s131K ctx
dense
👁 NVIDIA
Nemotron Nano 9B v2
A75
9B22.9 GB126 tok/s131K ctx
dense
👁 IBM
Granite Code 34B
A75
34B39.4 GB211 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek Coder V2 16B
A75
16B28.1 GB984 tok/s131K ctx
moe
👁 Defog
SQLCoder 7B
A75
7B21.2 GB98 tok/s8K ctx
dense
👁 Alibaba
Qwen 3 4B
A75
4B19.6 GB56 tok/s33K ctx
dense
👁 Alibaba
Qwen 2.5 VL 7B
A75
7B20.1 GB98 tok/s33K ctx
dense
👁 Cohere
Command R 35B
A74
35B38.8 GB205 tok/s131K ctx
dense
👁 Jina AI
Jina Embeddings v3
A74
0.57B18.1 GB8 tok/s8K ctx
dense
👁 BigCode
StarCoder 15B
A73
15B40.4 GB210 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 32B
A73
32B38.4 GB223 tok/s33K ctx
dense
👁 NVIDIA
Nemotron 70B
A73
70B62.6 GB103 tok/s131K ctx
dense
👁 Magistral AI
Magistral 7B
A73
7B21.2 GB98 tok/s8K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
A73
9B21.1 GB126 tok/s131K ctx
dense
👁 BAAI
BGE M3
A73
0.57B17.3 GB8 tok/s8K ctx
dense
👁 AllenAI
OLMo 2 13B
A73
13B25.4 GB182 tok/s33K ctx
dense
👁 Google
Gemma 4 E4B
A72
8B21.2 GB112 tok/s128K ctx
dense
👁 Meta
CodeLlama 13B Instruct
A72
13B35.1 GB182 tok/s16K ctx
dense
👁 MosaicML
MPT-30B-Instruct
A72
30B60.0 GB190 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 7B
A71
7B20.1 GB98 tok/s131K ctx
dense
👁 Cohere
Command R+ 104B
A71
104B81.9 GB69 tok/s131K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
A71
13B35.1 GB182 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 14B
A70
14B26.5 GB196 tok/s33K ctx
dense
👁 Mistral
Mixtral 8x22B
A70
141B104.4 GB97 tok/s66K ctx
moe
👁 IBM
Granite Code 8B
A70
8B21.8 GB112 tok/s8K ctx
dense
👁 DevStral AI
DevStral 7B
A70
7B21.2 GB98 tok/s8K ctx
dense
👁 Mistral AI
Codestral Mamba 7B
A70
7B19.8 GB98 tok/s262K ctx
state-space
B

B Tier -- Good Fit (58 models)

Solid performance, may need quantization or reduced context.

👁 IBM
Granite 4.1 8B
B69
8B22.3 GB112 tok/s131K ctx
dense
👁 TII
Falcon 40B Instruct
B69
40B45.6 GB155 tok/s8K ctx
dense
👁 Mixedbread AI
mxbai Embed Large
B69
0.34B17.2 GB5 tok/s1K ctx
dense
👁 Meta
CodeLlama 7B Instruct
B69
7B27.1 GB98 tok/s16K ctx
dense
👁 BigCode
StarCoder 7B
B69
7B26.6 GB98 tok/s8K ctx
dense
👁 Mistral AI
Pixtral 12B
B69
12B24.8 GB168 tok/s131K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
B68
0.34B17.2 GB5 tok/s1K ctx
dense
👁 Nous Research
Nous Dolphin 13B
B68
13B36.6 GB182 tok/s16K ctx
dense
👁 Google
Gemma 2 27B
B68
27B42.7 GB160 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 3B
B68
3B19.0 GB42 tok/s131K ctx
dense
👁 WizardLM
WizardLM 13B
B68
13B35.1 GB182 tok/s8K ctx
dense
👁 LMSYS
Vicuna 13B
B68
13B35.1 GB182 tok/s4K ctx
dense
👁 Nous Research
Nous Hermes 1.0
B67
9B32.7 GB126 tok/s16K ctx
dense
👁 Google
Gemma 4 E2B
B67
5.1B18.6 GB71 tok/s128K ctx
dense
👁 BAAI
BGE Large EN v1.5
B67
0.34B17.2 GB5 tok/s1K ctx
dense
👁 InternLM
InternLM 7B
B67
7B27.1 GB98 tok/s8K ctx
dense
👁 InternLM
InternLM Chat 7B
B67
7B27.1 GB98 tok/s8K ctx
dense
👁 Zhipu
GLM-4 9B
B66
9B21.1 GB126 tok/s128K ctx
dense
👁 Meta
Llama 3.1 8B
B66
8B21.8 GB112 tok/s128K ctx
dense
B66
7B22.2 GB98 tok/s8K ctx
dense
👁 WizardLM
WizardMath 7B
B66
7B21.2 GB98 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
B66
7B21.2 GB98 tok/s4K ctx
dense
👁 Nomic AI
Nomic Embed Text v1.5
B65
0.14B15.8 GB2 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
B65
72B63.8 GB100 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 7B
B65
7B20.1 GB98 tok/s131K ctx
dense
👁 Google
Gemma 3 4B
B65
4B19.5 GB56 tok/s128K ctx
dense
👁 Mistral
Ministral 3 3B
B64
3B17.6 GB42 tok/s262K ctx
multimodal
👁 Mistral
Mixtral 8x7B
B64
47B45.6 GB290 tok/s33K ctx
moe
👁 LLaVA
LLaVA 1.5 7B
B64
7B27.1 GB98 tok/s4K ctx
dense
👁 Microsoft
Phi 4 Mini 4B
B64
4B18.9 GB56 tok/s128K ctx
dense
👁 Baichuan
Baichuan 13B
B64
13B36.6 GB182 tok/s8K ctx
dense
👁 Cerebras
Cerebras-GPT 13B
B63
13B34.1 GB182 tok/s131K ctx
dense
👁 Alibaba
Qwen 3.5 2B
B63
2B17.9 GB28 tok/s131K ctx
dense
👁 MosaicML
MPT-7B-Instruct
B62
7B27.1 GB98 tok/s8K ctx
dense
👁 Baichuan
Baichuan 7B
B62
7B27.1 GB98 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 7B
B62
7B20.1 GB98 tok/s33K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 8B
B62
8B21.8 GB112 tok/s33K ctx
dense
7B21.2 GB98 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek LLM 67B
B61
67B61.7 GB107 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 3B
B61
3B19.0 GB42 tok/s131K ctx
dense
👁 TII
Falcon 7B Instruct
B61
7B19.4 GB98 tok/s8K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
B61
3.8B23.2 GB53 tok/s128K ctx
dense
👁 01.AI
Yi 1.5 34B
B60
34B39.4 GB211 tok/s4K ctx
dense
👁 Google
Gemma 2 9B
B60
9B25.6 GB126 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 14B
B60
14B26.5 GB196 tok/s131K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B60
1.7B17.7 GB24 tok/s33K ctx
dense
👁 Meta
Llama 3.2 11B Vision
B60
11B23.7 GB154 tok/s16K ctx
vision
B60
0.02B15.3 GB2 tok/s0K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
B60
4B23.3 GB56 tok/s128K ctx
dense
👁 IBM
Granite 4.1 3B
B59
3B18.1 GB42 tok/s131K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 1.5B
B58
1.5B16.3 GB21 tok/s33K ctx
dense
👁 IBM
Granite Code 3B
B58
3B19.3 GB42 tok/s8K ctx
dense
👁 Mistral
Mistral Nemo 12B
B58
12B24.8 GB168 tok/s128K ctx
dense
👁 01.AI
Yi Coder 9B
B57
9B22.0 GB126 tok/s131K ctx
dense
👁 Mistral
Mistral 7B Instruct v0.3
B57
7B21.2 GB98 tok/s8K ctx
dense
👁 InternLM
InternLM 20B
B57
20B47.7 GB280 tok/s8K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
B57
14B26.6 GB196 tok/s128K ctx
dense
👁 Mistral AI
Codestral 22B
B57
22B30.9 GB307 tok/s33K ctx
dense
C

C Tier -- Tight Fit (188 models)

Runs with offloading or significant compromises.

👁 Mistral
Ministral 8B
C55
8B22.1 GB112 tok/s131K ctx
dense
👁 Meta
Llama 3.2 3B
C55
3B18.5 GB42 tok/s128K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
C55
122B89.1 GB63 tok/s74K ctx
dense
Solar Open 100B
C54
100B87.7 GB66 tok/s89K ctx
dense
Solar Open 100B i1
C54
100B87.7 GB66 tok/s89K ctx
dense
👁 Cohere
Aya Expanse 32B
C53
32B37.0 GB225 tok/s8K ctx
dense
Llama 3.3 70B Instruct
C52
70B65.9 GB94 tok/s162K ctx
dense
BaichuanMed OCR 72B i1
C52
72B67.4 GB92 tok/s156K ctx
dense
Solar Open 69B REAP i1
C52
69B65.2 GB96 tok/s166K ctx
dense
stabilityai japanese stablelm instruct beta 70b
C51
70B65.9 GB94 tok/s162K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
C50
1.5B16.3 GB21 tok/s33K ctx
dense
👁 TinyLlama
TinyLlama 1.1B
C50
1.1B16.0 GB15 tok/s4K ctx
dense
C50
3B18.8 GB42 tok/s128K ctx
dense
👁 IBM
Granite 3.1 8B
C50
8B21.8 GB112 tok/s128K ctx
state-space
👁 01.AI
Yi 1.5 9B
C50
9B22.0 GB126 tok/s4K ctx
dense
👁 01.AI
Yi 34B Chat
C49
34B39.4 GB211 tok/s200K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
C49
48B49.9 GB138 tok/s275K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
C49
7B20.1 GB98 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
C48
35B40.5 GB189 tok/s408K ctx
dense
Qwen3.5 35B A3B
C48
35B40.5 GB189 tok/s408K ctx
dense
Hermes 4.3 36B
C48
36B41.2 GB184 tok/s395K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
C48
1.5B16.3 GB21 tok/s131K ctx
dense
👁 Unsloth
Qwen3.5 27B
C48
27B34.6 GB245 tok/s554K ctx
dense
EXAONE 4.0 32B
C47
32B38.3 GB207 tok/s454K ctx
dense
aya expanse 32b heretic MPOA i1
C47
32B38.3 GB207 tok/s454K ctx
dense
👁 Unsloth
gemma 3 27b it
C47
27B34.6 GB245 tok/s554K ctx
dense
Baichuan M2 32B Q4 K M
C47
32B38.3 GB207 tok/s454K ctx
dense
👁 BigCode
StarCoder2 15B
C47
15B27.0 GB210 tok/s16K ctx
dense
baichuan inc Baichuan M2 32B
C47
32B38.3 GB207 tok/s454K ctx
dense
gemma 3 27b it
C47
27B34.6 GB245 tok/s554K ctx
dense
👁 OpenChat
OpenChat 7B
C47
7B21.2 GB98 tok/s8K ctx
dense
👁 Stability AI
StableLM 2 12B
C47
12B35.8 GB168 tok/s4K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
C47
24B32.5 GB275 tok/s634K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C47
24B32.5 GB275 tok/s634K ctx
dense
Mistral Small 24B Instruct 2501
C47
24B32.5 GB275 tok/s634K ctx
dense
mistral small 3.1 24b instruct 2503 hf
C47
24B32.5 GB275 tok/s634K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
C47
24B32.5 GB275 tok/s634K ctx
dense
👁 Cohere
Aya Expanse 8B
C47
8B21.8 GB112 tok/s8K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
C47
24B32.5 GB275 tok/s634K ctx
dense
👁 LMSYS
Vicuna 7B
C47
7B27.1 GB98 tok/s4K ctx
dense
Codestral 22B v0.1
C47
22B31.0 GB300 tok/s699K ctx
dense
Codestral 22B v0.1
C47
22B31.0 GB300 tok/s699K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C46
24B32.5 GB275 tok/s634K ctx
dense
Codestral 22B v0.1
C46
22B31.0 GB300 tok/s699K ctx
dense
👁 Google
Gemma 3 1B
C46
1B16.0 GB14 tok/s33K ctx
dense
Codestral 22B v0.1 IMat
C46
22B31.0 GB300 tok/s699K ctx
dense
Codestral 22B v0.1 i1
C46
22B31.0 GB300 tok/s699K ctx
dense
Codestral 21B Pruned i1
C46
21B30.3 GB294 tok/s736K ctx
dense
internlm2 5 20b chat
C46
20B29.5 GB280 tok/s777K ctx
dense
internlm2 limarp chat 20b
C46
20B29.5 GB280 tok/s777K ctx
dense
👁 Teknium
OpenHermes 2.5 7B
C46
7B21.2 GB98 tok/s8K ctx
dense
internlm2 math plus 20b i1
C46
20B29.5 GB280 tok/s777K ctx
dense
8B21.8 GB112 tok/s33K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
C46
14B25.2 GB196 tok/s1146K ctx
dense
Phi 4 reasoning vision 15B
C46
15B25.9 GB210 tok/s1064K ctx
dense
Codestral RAG 19B Pruned i1
C46
19B28.8 GB266 tok/s822K ctx
dense
StarCoder2 15B
C46
15B25.9 GB210 tok/s1064K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
C46
7B21.2 GB98 tok/s33K ctx
dense
NousResearch Hermes 4 14B
C46
14B25.2 GB196 tok/s1146K ctx
dense
gemma 3 12b it
C46
12B23.7 GB168 tok/s1350K ctx
dense
👁 Unsloth
Qwen3.5 9B
C46
9B21.5 GB126 tok/s1828K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C45
9B21.5 GB126 tok/s1828K ctx
dense
starcoder2 15b instruct v0.1
C45
15B25.9 GB210 tok/s1064K ctx
dense
starcoder2 15b i1
C45
15B25.9 GB210 tok/s1064K ctx
dense
👁 Google
Gemma 2 2B
C45
2B17.8 GB28 tok/s8K ctx
dense
starcoder2 15b instruct v0.1
C45
15B25.9 GB210 tok/s1064K ctx
dense
👁 UC Berkeley
Starling LM 7B
C45
7B21.2 GB98 tok/s8K ctx
dense
Meta Llama 3.1 8B Instruct
C45
8B20.8 GB112 tok/s2067K ctx
dense
Qwen3.5 9B
C45
9B21.5 GB126 tok/s1828K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
C45
14B25.2 GB196 tok/s1146K ctx
dense
HelpingAI 15B i1
C45
15B25.9 GB210 tok/s1064K ctx
dense
llava llama 3 8b v1 1
C45
8B20.8 GB112 tok/s2067K ctx
dense
internlm JanusCoder 14B
C45
14B25.2 GB196 tok/s1146K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
C45
8B20.8 GB112 tok/s2067K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
C45
14B25.2 GB196 tok/s1146K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C45
10.7B22.8 GB150 tok/s1524K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C45
10.7B22.8 GB150 tok/s1524K ctx
dense
Meta Llama 3 8B Instruct
C45
8B20.8 GB112 tok/s2067K ctx
dense
Llama 2 7B Chat
C45
7B20.1 GB98 tok/s2374K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
C45
8B20.8 GB112 tok/s2067K ctx
dense
Dolphin3.0 Llama3.1 8B
C45
8B20.8 GB112 tok/s2067K ctx
dense
Llama 3 8B Instruct 32k v0.1
C45
8B20.8 GB112 tok/s2067K ctx
dense
Yi Coder 9B Chat
C45
9B21.5 GB126 tok/s1828K ctx
dense
Mistral 7B Instruct v0.2
C45
7B20.1 GB98 tok/s2374K ctx
dense
Meta Llama 3.1 8B Instruct
C45
8B20.8 GB112 tok/s2067K ctx
dense
vntl llama3 8b v2
C45
8B20.8 GB112 tok/s2067K ctx
dense
glm 4 9b chat 1m
C45
9B21.5 GB126 tok/s1828K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C45
8B20.8 GB112 tok/s2067K ctx
dense
Mistral 7B Instruct v0.3
C45
7B20.1 GB98 tok/s2374K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C45
8B20.8 GB112 tok/s2067K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C45
8B20.8 GB112 tok/s2067K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C45
0.5B15.5 GB7 tok/s131K ctx
dense
Hermes 3 Llama 3.1 8B
C45
8B20.8 GB112 tok/s2067K ctx
dense
Yi 1.5 9B Chat
C45
9B21.5 GB126 tok/s1828K ctx
dense
solar finalised finetuned Model 10.7B i1
C45
10.7B22.8 GB150 tok/s1524K ctx
dense
Hermes 2 Pro Llama 3 8B
C45
8B20.8 GB112 tok/s2067K ctx
dense
Dolphin3.0 Llama3.1 8B
C45
8B20.8 GB112 tok/s2067K ctx
dense
granite 8b code instruct 4k
C45
8B20.8 GB112 tok/s2067K ctx
dense
SOLAR 10.7B v1.0
C45
10.7B22.8 GB150 tok/s1524K ctx
dense
dolphin 2.9.4 llama3.1 8b
C45
8B20.8 GB112 tok/s2067K ctx
dense
Mistral 7B Instruct v0.3
C45
7B20.1 GB98 tok/s2374K ctx
dense
Hermes 2 Pro Mistral 7B
C45
7B20.1 GB98 tok/s2374K ctx
dense
zephyr 7B beta
C45
7B20.1 GB98 tok/s2374K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C45
7B20.1 GB98 tok/s2374K ctx
dense
openchat 3.6 8b 20240522 IMat
C45
8B20.8 GB112 tok/s2067K ctx
dense
aya expanse 8b
C45
8B20.8 GB112 tok/s2067K ctx
dense
EXAONE 3.5 7.8B Instruct
C45
7.8B20.7 GB109 tok/s2122K ctx
dense
Falcon H1R 7B
C45
7B20.1 GB98 tok/s2374K ctx
dense
Yi 9B Coder i1
C45
9B21.5 GB126 tok/s1828K ctx
dense
dolphin v2 8b abliterated i1
C45
8B20.8 GB112 tok/s2067K ctx
dense
EXAONE 3.5 7.8B Instruct
C45
7.8B20.7 GB109 tok/s2122K ctx
dense
falcon mamba 7b instruct Q4 K M
C45
7B20.1 GB98 tok/s2374K ctx
dense
zephyr 7B alpha
C45
7B20.1 GB98 tok/s2374K ctx
dense
speechless zephyr code functionary 7b
C45
7B20.1 GB98 tok/s2374K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C45
7.8B20.7 GB109 tok/s2122K ctx
dense
HelpingAI2.5 10B i1
C45
10B22.3 GB140 tok/s1637K ctx
dense
aya expanse 8b orthogonal heretic i1
C45
8B20.8 GB112 tok/s2067K ctx
dense
Helply 10.2b chat i1
C45
10.2B22.4 GB143 tok/s1603K ctx
dense
StarCoder2 7B
C45
7B20.1 GB98 tok/s2374K ctx
dense
exaone 3.0 7.8b it
C45
7.8B20.7 GB109 tok/s2122K ctx
dense
HelpingAI2 9B
C45
9B21.5 GB126 tok/s1828K ctx
dense
japanese stablelm instruct gamma 7B
C45
7B20.1 GB98 tok/s2374K ctx
dense
Falcon H1 7B Instruct
C45
7B20.1 GB98 tok/s2374K ctx
dense
👁 Unsloth
Falcon H1R 7B
C45
7B20.1 GB98 tok/s2374K ctx
dense
HelpingAI2 9B i1
C45
9B21.5 GB126 tok/s1828K ctx
dense
HelpingAI 9B 200k i1
C45
9B21.5 GB126 tok/s1828K ctx
dense
aya expanse 8b orthogonal heretic
C45
8B20.8 GB112 tok/s2067K ctx
dense
Yi 1.5 6B Chat
C45
6B19.4 GB84 tok/s2784K ctx
dense
HelpingAI 9B i1
C45
9B21.5 GB126 tok/s1828K ctx
dense
Mamba Codestral 7B v0.1
C45
7B20.1 GB98 tok/s2374K ctx
dense
stablelm 2 zephyr 1 6b
C45
6B19.4 GB84 tok/s2784K ctx
dense
stabilityai japanese stablelm base gamma 7b
C45
7B20.1 GB98 tok/s2374K ctx
dense
internlm2 5 1 8b chat i1
C45
8B20.8 GB112 tok/s2067K ctx
dense
internlm3 8b instruct abliterated i1
C45
8B20.8 GB112 tok/s2067K ctx
dense
baichuan2 7b chat
C45
7B20.1 GB98 tok/s2374K ctx
dense
DiscoPOP zephyr 7b gemma
C45
7B20.1 GB98 tok/s2374K ctx
dense
starcoder2 7b
C44
7B20.1 GB98 tok/s2374K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C44
7B20.1 GB98 tok/s2374K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C44
7B20.1 GB98 tok/s2374K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C44
7B20.1 GB98 tok/s2374K ctx
dense
internlm2 math plus 7b IMat
C44
7B20.1 GB98 tok/s2374K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C44
7B20.1 GB98 tok/s2374K ctx
dense
internlm2 5 7b chat i1
C44
7B20.1 GB98 tok/s2374K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C44
7B20.1 GB98 tok/s2374K ctx
dense
MD Judge v0 2 internlm2 7b i1
C44
7B20.1 GB98 tok/s2374K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C44
7B20.1 GB98 tok/s2374K ctx
dense
jointpreferences mistral 7b sft helpful
C44
7B20.1 GB98 tok/s2374K ctx
dense
👁 01.AI
Yi 1.5 6B
C44
6B19.6 GB84 tok/s4K ctx
dense
Yi 1.5 6B Chat
C44
6B19.4 GB84 tok/s2784K ctx
dense
zephyr 7b dpo full i1
C44
7B20.1 GB98 tok/s2374K ctx
dense
blossom v3 baichuan2 7b i1
C44
7B20.1 GB98 tok/s2374K ctx
dense
stablelm 2 1 6b chat imatrix
C44
6B19.4 GB84 tok/s2784K ctx
dense
blossom v1 baichuan 7b i1
C44
7B20.1 GB98 tok/s2374K ctx
dense
👁 Intel
Neural Chat 7B
C44
7B21.2 GB98 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek LLM 7B
C44
7B26.6 GB98 tok/s4K ctx
dense
HelpingAI2 6B
C44
6B19.4 GB84 tok/s2784K ctx
dense
👁 BigCode
StarCoder2 7B
C44
7B19.8 GB98 tok/s16K ctx
dense
HelpingAI2 6B i1
C44
6B19.4 GB84 tok/s2784K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
C44
4B19.4 GB56 tok/s4K ctx
dense
HelpingAI2.5 5B i1
C43
5B18.6 GB70 tok/s3357K ctx
dense
👁 Unsloth
Qwen3.5 4B
C43
4B17.9 GB56 tok/s4218K ctx
dense
gemma 3 4b it
C43
4B17.9 GB56 tok/s4218K ctx
dense
gemma 3 4b it
C43
4B17.9 GB56 tok/s4218K ctx
dense
👁 Alibaba
Qwen 3 0.6B
C43
0.6B16.2 GB8 tok/s33K ctx
dense
👁 Meta
Llama 3.2 1B
C43
1B16.1 GB14 tok/s128K ctx
dense
Llama 3.2 3B Instruct
C42
3B17.5 GB42 tok/s5636K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C42
3B17.2 GB42 tok/s5651K ctx
dense
Llama 3.2 3B Instruct
C42
3B17.2 GB42 tok/s5651K ctx
dense
Ministral 3 3B Instruct 2512
C42
3B17.2 GB42 tok/s5651K ctx
dense
HELVETE 3B
C42
3B17.2 GB42 tok/s5651K ctx
dense
Hermes 3 Llama 3.2 3B
C42
3B17.2 GB42 tok/s5651K ctx
dense
stablelm zephyr 3b
C42
3B17.2 GB42 tok/s5651K ctx
dense
StarCoder2 3B
C42
3B17.2 GB42 tok/s5651K ctx
dense
AI21 Jamba Reasoning 3B
C42
3B17.2 GB42 tok/s5651K ctx
dense
stablelm 3b 4e1t
C42
3B17.2 GB42 tok/s5651K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C42
3B17.2 GB42 tok/s5651K ctx
dense
ai21labs AI21 Jamba2 3B
C42
3B17.2 GB42 tok/s5651K ctx
dense
HelpingAI 3B hindi i1
C41
3B17.2 GB42 tok/s5651K ctx
dense
AI21 Jamba2 3B
C41
3B17.2 GB42 tok/s5651K ctx
dense
HelpingAI 3B hindi
C41
3B17.2 GB42 tok/s5651K ctx
dense
AI21 Jamba2 3B i1
C41
3B17.2 GB42 tok/s5651K ctx
dense
EXAONE 3.5 2.4B Instruct
C41
2.4B16.7 GB34 tok/s7085K ctx
dense
gemma 2 2b it
C41
2B16.9 GB28 tok/s8490K ctx
dense
👁 Google
gemma 2b
C41
2B16.5 GB28 tok/s8518K ctx
dense
Gemmasutra Mini 2B v1
C41
2B16.5 GB28 tok/s8518K ctx
dense
👁 Alibaba
Qwen 3.5 0.6B
C41
0.6B16.2 GB8 tok/s131K ctx
dense
gemma 2 2b it
C41
2B16.5 GB28 tok/s8518K ctx
dense
👁 BigCode
StarCoder2 3B
C41
3B17.3 GB42 tok/s16K ctx
dense
F

F Tier -- Can't Run (42 models)

Too heavy for this hardware.

👁 Qwen
Qwen2.5 1.5B Instruct
D40
1.5B16.1 GB21 tok/s11386K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B
D40
1.5B16.1 GB21 tok/s11386K ctx
dense
Yi Coder 1.5B Chat
D40
1.5B16.1 GB21 tok/s11386K ctx
dense
stablelm 2 zephyr 1.6b
D39
1.6B16.2 GB22 tok/s10669K ctx
dense
logos16v2 stablelm2 1.6b i1
D39
1.6B16.2 GB22 tok/s10669K ctx
dense
Yi Coder 1.5B
D39
1.5B16.1 GB21 tok/s11386K ctx
dense
👁 Unsloth
Falcon H1 1.5B Instruct
D39
1.5B16.1 GB21 tok/s11386K ctx
dense
TinyLlama 1.1B Chat v1.0
D39
1.1B15.8 GB15 tok/s15556K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
D39
0.5B15.5 GB7 tok/s131K ctx
dense
EXAONE 4.0 1.2B
D39
1.2B15.9 GB17 tok/s14253K ctx
dense
Llama 3.2 1B Instruct Q8 0
D39
1B15.9 GB14 tok/s17091K ctx
dense
TinyLlama 1.1B Chat v0.3
D39
1.1B15.8 GB15 tok/s15556K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
D39
1.1B15.8 GB15 tok/s15556K ctx
dense
Llama 3.2 1B Instruct
D38
1B15.7 GB14 tok/s17120K ctx
dense
gemma 3 1b it
D38
1B15.7 GB14 tok/s17120K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
D38
1.1B15.8 GB15 tok/s15556K ctx
dense
Falcon3 1B Instruct abliterated
D38
1B15.7 GB14 tok/s17120K ctx
dense
SmolVLM 500M Instruct
D36
0.5B15.5 GB7 tok/s20094K ctx
dense
embeddinggemma 300M
D35
0.3B15.3 GB4 tok/s20121K ctx
dense
granite embedding 107m multilingual
D33
0.11B15.2 GB2 tok/s20150K ctx
dense
Falcon H1 Tiny 90M Instruct
D33
0.09B15.2 GB2 tok/s20151K ctx
dense
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B310.7 GB6 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B260.0 GB12 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B432.1 GB5 tok/s4K ctx
+1moe
F0
744B487.9 GB4 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B494.0 GB4 tok/s4K ctx
moe
F0
1000B632.4 GB3 tok/s4K ctx
moe
F0
1000B632.4 GB3 tok/s4K ctx
+1moe
👁 DeepSeek
DeepSeek V3 671B
F0
671B483.9 GB4 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B483.9 GB4 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B878.9 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Flash
F0
284B174.3 GB43 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B483.9 GB4 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B217.6 GB24 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B217.6 GB24 tok/s4K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B261.9 GB12 tok/s4K ctx
moe
👁 Meta
Llama 3.1 405B
F0
405B269.7 GB4 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B424.8 GB5 tok/s4K ctx
moe
K EXAONE 236B A23B
F0
236B186.6 GB12 tok/s4K ctx
dense
Baichuan M3 235B
F0
235B185.9 GB12 tok/s4K ctx
dense
Baichuan M3 235B i1
F0
235B185.9 GB12 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 397B A17B
F0
397B303.7 GB3 tok/s4K ctx
dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

NVIDIA H200 141GB

141 GB VRAM

View tier list

AMD Instinct MI250X 128GB

128 GB VRAM

View tier list

AMD Instinct MI300A 128GB

128 GB VRAM

View tier list

Intel Data Center GPU Max 1550 128GB

128 GB VRAM

View tier list
Full NVIDIA H200 PCIe 141GB pageCompare this hardware