VOOZH about

URL: https://willitrunai.com/my-results/b200-180gb

⇱ NVIDIA B200 180GB AI Tier List: 336 models ranked | WillItRunAI


AI Compatibility Tier List

NVIDIA B200 180GB

374 AI models ranked by how well they run on your 180 GB VRAM hardware. Best match: Devstral 2 123B Instruct (score: 97).

374

Models tested

336

Can run

180 GB

VRAM

97

Best tok/s

Tier Distribution

S 27
A 54
B 64
C 191
F 38
S: 27A: 54B: 64C: 191F: 38
S

S Tier -- Perfect Fit (27 models)

These models run flawlessly with headroom to spare.

👁 Mistral
Devstral 2 123B Instruct
S97
123B99.3 GB97 tok/s256K ctx
dense
👁 DeepSeek
DeepSeek V4 Flash
S96
284B178.2 GB145 tok/s38K ctx
moe
👁 Alibaba
Qwen 3.5 122B A10B
S96
122B95.8 GB270 tok/s131K ctx
moe
👁 Mistral
Mistral Small 4 119B
S94
119B96.9 GB293 tok/s256K ctx
moe
👁 OpenAI
GPT-OSS 120B
S94
117B95.2 GB102 tok/s131K ctx
dense
👁 Mistral AI
Pixtral Large 124B
S93
124B99.9 GB97 tok/s131K ctx
dense
👁 Cohere
Command A 111B
S93
111B90.5 GB108 tok/s262K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
S92
235B165.1 GB137 tok/s99K ctx
moe
👁 Alibaba
Qwen 2.5 VL 72B
S90
72B67.7 GB166 tok/s33K ctx
dense
MiniMax M2.7
S90
230B163.0 GB156 tok/s88K ctx
moe
👁 Alibaba
Qwen3-Coder-Next
S90
80B69.2 GB454 tok/s256K ctx
moe
👁 Mistral
Leanstral 119B A6B
S90
119B100.3 GB269 tok/s161K ctx
moe
👁 Alibaba
Qwen3-Coder 30B A3B Instruct
S90
30.5B39.0 GB1016 tok/s256K ctx
moe
👁 Alibaba
Qwen 3.6 35B A3B
S89
35B44.4 GB854 tok/s262K ctx
+1moe
👁 Alibaba
Qwen 3.5 27B
S89
27B38.5 GB378 tok/s131K ctx
dense
👁 Alibaba
Qwen3-VL 30B A3B Instruct
S89
30B38.7 GB1051 tok/s256K ctx
moe
👁 Alibaba
Qwen 3.6 27B
S89
27B36.3 GB275 tok/s262K ctx
+1dense
👁 Alibaba
Qwen 3.5 35B A3B
S88
35B41.7 GB929 tok/s131K ctx
moe
👁 Alibaba
Qwen 3 32B
S88
32B42.3 GB374 tok/s131K ctx
dense
👁 Mistral
Magistral Small 2507
S88
24B36.0 GB336 tok/s131K ctx
dense
👁 Mistral
Devstral Small 2 24B Instruct
S87
24B36.0 GB336 tok/s256K ctx
dense
👁 Alibaba
Qwen 3 30B A3B
S87
30.5B39.0 GB1016 tok/s131K ctx
moe
👁 NVIDIA
Nemotron 3 Nano 30B
S87
30B39.6 GB395 tok/s131K ctx
dense
👁 Alibaba
Qwen 3.5 9B
S87
9B26.6 GB126 tok/s131K ctx
dense
👁 Alibaba
Qwen 3 14B
S86
14B29.9 GB196 tok/s131K ctx
dense
👁 Mistral
Devstral Small 1.1
S86
24B36.0 GB336 tok/s131K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
S85
14.7B30.9 GB206 tok/s33K ctx
dense
A

A Tier -- Great Fit (54 models)

Excellent performance with comfortable memory margins.

👁 Google
Gemma 4 31B
A85
30.7B52.3 GB234 tok/s156K ctx
dense
👁 Alibaba
Qwen 3 8B
A85
8B26.0 GB112 tok/s131K ctx
dense
👁 OpenAI
GPT-OSS 20B
A84
21B34.2 GB1290 tok/s128K ctx
moe
👁 NVIDIA
Nemotron Cascade 2 30B A3B
A84
30B40.1 GB1039 tok/s262K ctx
moe
👁 Meta
Llama 3.3 70B
A84
70B66.5 GB171 tok/s128K ctx
dense
👁 Alibaba
Qwen 3.5 4B
A83
4B23.5 GB56 tok/s131K ctx
dense
👁 LG AI
EXAONE 4.0 32B
A82
32B42.3 GB372 tok/s131K ctx
dense
👁 Google
Gemma 4 26B A4B
A81
25.2B37.9 GB1091 tok/s256K ctx
moe
👁 Alibaba
Qwen 2.5 72B
A81
72B67.7 GB166 tok/s131K ctx
dense
👁 Meta
Llama 3.1 70B
A81
70B66.5 GB171 tok/s128K ctx
dense
👁 Mistral
Ministral 3 14B
A80
14B29.9 GB196 tok/s262K ctx
multimodal
👁 Alibaba
Qwen 2.5 32B
A80
32B42.3 GB372 tok/s131K ctx
dense
👁 Mistral
Codestral 2 25.08
A80
22B34.8 GB308 tok/s256K ctx
dense
👁 Meta
Llama 4 Scout 17B 16E
A80
109B88.3 GB257 tok/s517K ctx
moe
👁 Mistral
Mistral Small 3.2 24B
A80
24B36.0 GB336 tok/s131K ctx
vision
👁 Moonshot AI
Kimi Linear 48B A3B
A80
48B49.1 GB230 tok/s1049K ctx
linear
👁 NVIDIA
Nemotron Nano 8B
A80
8B25.7 GB112 tok/s131K ctx
dense
👁 Google
Gemma 3 27B
A80
27B46.6 GB266 tok/s131K ctx
dense
👁 Microsoft
Phi-4 Mini Reasoning 4B
A80
3.8B22.7 GB53 tok/s131K ctx
dense
A79
24B36.0 GB336 tok/s131K ctx
dense
👁 Allen AI
OLMo 2 32B
A79
32B42.3 GB372 tok/s4K ctx
dense
👁 IBM
Granite 4.1 30B
A79
30B41.1 GB395 tok/s131K ctx
dense
A79
19B32.9 GB266 tok/s8K ctx
dense
👁 Mistral
Mistral Small 24B
A78
24B36.0 GB336 tok/s33K ctx
dense
👁 Mistral AI
Mistral Small 3.1 24B
A77
24B36.0 GB336 tok/s131K ctx
dense
👁 InternLM
InternVL2 8B
A77
8B25.7 GB112 tok/s8K ctx
dense
A77
14B30.5 GB196 tok/s16K ctx
dense
👁 Alibaba
Qwen 2.5 14B
A76
14B30.4 GB196 tok/s131K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
A76
70B66.5 GB171 tok/s131K ctx
dense
👁 IBM
Granite Code 20B
A76
20B34.3 GB280 tok/s8K ctx
dense
👁 Mistral
Ministral 3 8B
A75
8B26.0 GB112 tok/s262K ctx
multimodal
👁 OpenBMB
MiniCPM-V 2.6 8B
A75
8B25.7 GB112 tok/s2K ctx
dense
👁 Google
Gemma 3 12B
A75
12B31.1 GB168 tok/s131K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 32B
A75
32B42.3 GB372 tok/s131K ctx
dense
👁 Alibaba
Qwen 3 4B
A75
4B23.5 GB56 tok/s33K ctx
dense
👁 NVIDIA
Nemotron Nano 9B v2
A75
9B26.8 GB126 tok/s131K ctx
dense
👁 Defog
SQLCoder 7B
A74
7B25.1 GB98 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 VL 7B
A74
7B24.0 GB98 tok/s33K ctx
dense
👁 DeepSeek
DeepSeek Coder V2 16B
A74
16B32.0 GB1639 tok/s131K ctx
moe
👁 IBM
Granite Code 34B
A74
34B43.3 GB351 tok/s8K ctx
dense
👁 Jina AI
Jina Embeddings v3
A74
0.57B22.0 GB8 tok/s8K ctx
dense
👁 Cohere
Command R 35B
A73
35B42.7 GB342 tok/s131K ctx
dense
👁 Magistral AI
Magistral 7B
A73
7B25.1 GB98 tok/s8K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
A73
9B25.0 GB126 tok/s131K ctx
dense
👁 BAAI
BGE M3
A73
0.57B21.2 GB8 tok/s8K ctx
dense
👁 AllenAI
OLMo 2 13B
A72
13B29.3 GB182 tok/s33K ctx
dense
👁 BigCode
StarCoder 15B
A72
15B44.3 GB210 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 32B
A72
32B42.3 GB372 tok/s33K ctx
dense
👁 Google
Gemma 4 E4B
A72
8B25.1 GB112 tok/s128K ctx
dense
👁 Meta
CodeLlama 13B Instruct
A72
13B39.0 GB182 tok/s16K ctx
dense
👁 NVIDIA
Nemotron 70B
A71
70B66.5 GB171 tok/s131K ctx
dense
👁 Alibaba
Qwen 2.5 7B
A71
7B24.0 GB98 tok/s131K ctx
dense
👁 MosaicML
MPT-30B-Instruct
A70
30B63.9 GB317 tok/s8K ctx
dense
👁 IBM
Granite Code 8B
A70
8B25.7 GB112 tok/s8K ctx
dense
B

B Tier -- Good Fit (64 models)

Solid performance, may need quantization or reduced context.

👁 DeepSeek
DeepSeek R1 Distill 14B
B70
14B30.4 GB196 tok/s33K ctx
dense
👁 DevStral AI
DevStral 7B
B70
7B25.1 GB98 tok/s8K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
B70
13B39.0 GB182 tok/s4K ctx
dense
👁 Mistral AI
Codestral Mamba 7B
B70
7B23.7 GB98 tok/s262K ctx
state-space
👁 Cohere
Command R+ 104B
B69
104B85.8 GB115 tok/s131K ctx
dense
👁 Mixedbread AI
mxbai Embed Large
B69
0.34B21.1 GB5 tok/s1K ctx
dense
👁 IBM
Granite 4.1 8B
B69
8B26.2 GB112 tok/s131K ctx
dense
👁 Meta
CodeLlama 7B Instruct
B69
7B31.0 GB98 tok/s16K ctx
dense
👁 Mistral AI
Pixtral 12B
B69
12B28.7 GB168 tok/s131K ctx
dense
👁 BigCode
StarCoder 7B
B69
7B30.5 GB98 tok/s8K ctx
dense
👁 TII
Falcon 40B Instruct
B68
40B49.5 GB259 tok/s8K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
B68
0.34B21.1 GB5 tok/s1K ctx
dense
👁 Mistral
Mixtral 8x22B
B68
141B108.3 GB162 tok/s66K ctx
moe
👁 Alibaba
Qwen 2.5 Coder 3B
B68
3B22.9 GB42 tok/s131K ctx
dense
👁 Nous Research
Nous Dolphin 13B
B67
13B40.5 GB182 tok/s16K ctx
dense
👁 WizardLM
WizardLM 13B
B67
13B39.0 GB182 tok/s8K ctx
dense
👁 LMSYS
Vicuna 13B
B67
13B39.0 GB182 tok/s4K ctx
dense
👁 Google
Gemma 2 27B
B67
27B46.6 GB266 tok/s8K ctx
dense
👁 Nous Research
Nous Hermes 1.0
B67
9B36.6 GB126 tok/s16K ctx
dense
👁 Google
Gemma 4 E2B
B67
5.1B22.5 GB71 tok/s128K ctx
dense
👁 BAAI
BGE Large EN v1.5
B67
0.34B21.1 GB5 tok/s1K ctx
dense
👁 Zhipu
GLM-4 9B
B66
9B25.0 GB126 tok/s128K ctx
dense
👁 InternLM
InternLM 7B
B66
7B31.0 GB98 tok/s8K ctx
dense
👁 InternLM
InternLM Chat 7B
B66
7B31.0 GB98 tok/s8K ctx
dense
👁 Meta
Llama 3.1 8B
B66
8B25.7 GB112 tok/s128K ctx
dense
B66
7B26.1 GB98 tok/s8K ctx
dense
👁 WizardLM
WizardMath 7B
B65
7B25.1 GB98 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
B65
7B25.1 GB98 tok/s4K ctx
dense
👁 Nomic AI
Nomic Embed Text v1.5
B65
0.14B19.7 GB2 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 7B
B65
7B24.0 GB98 tok/s131K ctx
dense
👁 Mistral
Ministral 3 3B
B64
3B21.5 GB42 tok/s262K ctx
multimodal
👁 Google
Gemma 3 4B
B64
4B23.4 GB56 tok/s128K ctx
dense
👁 Microsoft
Phi 4 Mini 4B
B64
4B22.8 GB56 tok/s128K ctx
dense
👁 LLaVA
LLaVA 1.5 7B
B63
7B31.0 GB98 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
B63
72B67.7 GB166 tok/s4K ctx
dense
👁 Mistral
Mixtral 8x7B
B63
47B49.5 GB483 tok/s33K ctx
moe
👁 Alibaba
Qwen 3.5 2B
B63
2B21.8 GB28 tok/s131K ctx
dense
👁 Baichuan
Baichuan 13B
B63
13B40.5 GB182 tok/s8K ctx
dense
👁 Cerebras
Cerebras-GPT 13B
B63
13B38.0 GB182 tok/s131K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 7B
B62
7B24.0 GB98 tok/s33K ctx
dense
👁 MosaicML
MPT-7B-Instruct
B62
7B31.0 GB98 tok/s8K ctx
dense
👁 Baichuan
Baichuan 7B
B62
7B31.0 GB98 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 8B
B61
8B25.7 GB112 tok/s33K ctx
dense
7B25.1 GB98 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 3B
B61
3B22.9 GB42 tok/s131K ctx
dense
👁 TII
Falcon 7B Instruct
B61
7B23.3 GB98 tok/s8K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
B60
3.8B27.1 GB53 tok/s128K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B60
1.7B21.6 GB24 tok/s33K ctx
dense
👁 Google
Gemma 2 9B
B60
9B29.5 GB126 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 14B
B60
14B30.4 GB196 tok/s131K ctx
dense
B60
0.02B19.2 GB2 tok/s0K ctx
dense
👁 01.AI
Yi 1.5 34B
B60
34B43.3 GB352 tok/s4K ctx
dense
👁 Meta
Llama 3.2 11B Vision
B60
11B27.6 GB154 tok/s16K ctx
vision
👁 DeepSeek
DeepSeek LLM 67B
B60
67B65.6 GB179 tok/s4K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
B59
4B27.2 GB56 tok/s128K ctx
dense
👁 IBM
Granite 4.1 3B
B59
3B22.0 GB42 tok/s131K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 1.5B
B58
1.5B20.2 GB21 tok/s33K ctx
dense
👁 IBM
Granite Code 3B
B58
3B23.2 GB42 tok/s8K ctx
dense
👁 Mistral
Mistral Nemo 12B
B58
12B28.7 GB168 tok/s128K ctx
dense
👁 01.AI
Yi Coder 9B
B57
9B25.9 GB126 tok/s131K ctx
dense
👁 Mistral
Mistral 7B Instruct v0.3
B57
7B25.1 GB98 tok/s8K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
B57
14B30.5 GB196 tok/s128K ctx
dense
👁 Mistral AI
Codestral 22B
B56
22B34.8 GB308 tok/s33K ctx
dense
👁 InternLM
InternLM 20B
B56
20B51.6 GB280 tok/s8K ctx
dense
C

C Tier -- Tight Fit (191 models)

Runs with offloading or significant compromises.

👁 Meta
Llama 3.2 3B
C55
3B22.4 GB42 tok/s128K ctx
dense
👁 Mistral
Ministral 8B
C54
8B26.0 GB112 tok/s131K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
C53
122B93.0 GB105 tok/s113K ctx
dense
Solar Open 100B
C53
100B91.6 GB110 tok/s137K ctx
dense
Solar Open 100B i1
C53
100B91.6 GB110 tok/s137K ctx
dense
👁 Cohere
Aya Expanse 32B
C52
32B40.9 GB374 tok/s8K ctx
dense
Llama 3.3 70B Instruct
C50
70B69.8 GB157 tok/s231K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
C50
1.5B20.2 GB21 tok/s33K ctx
dense
👁 TinyLlama
TinyLlama 1.1B
C50
1.1B19.9 GB15 tok/s4K ctx
dense
Solar Open 69B REAP i1
C50
69B69.1 GB160 tok/s235K ctx
dense
C50
3B22.7 GB42 tok/s128K ctx
dense
BaichuanMed OCR 72B i1
C50
72B71.3 GB153 tok/s222K ctx
dense
stabilityai japanese stablelm instruct beta 70b
C50
70B69.8 GB157 tok/s231K ctx
dense
👁 IBM
Granite 3.1 8B
C50
8B25.7 GB112 tok/s128K ctx
state-space
👁 01.AI
Yi 1.5 9B
C49
9B25.9 GB126 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
C49
7B24.0 GB98 tok/s4K ctx
dense
👁 01.AI
Yi 34B Chat
C49
34B43.3 GB352 tok/s200K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
C48
48B53.8 GB230 tok/s375K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
C48
1.5B20.2 GB21 tok/s131K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
C48
35B44.4 GB315 tok/s545K ctx
dense
Qwen3.5 35B A3B
C47
35B44.4 GB315 tok/s545K ctx
dense
Hermes 4.3 36B
C47
36B45.1 GB306 tok/s528K ctx
dense
👁 BigCode
StarCoder2 15B
C47
15B30.9 GB210 tok/s16K ctx
dense
👁 OpenChat
OpenChat 7B
C47
7B25.1 GB98 tok/s8K ctx
dense
👁 Unsloth
Qwen3.5 27B
C47
27B38.5 GB378 tok/s731K ctx
dense
👁 Unsloth
gemma 3 27b it
C47
27B38.5 GB378 tok/s731K ctx
dense
EXAONE 4.0 32B
C47
32B42.2 GB344 tok/s604K ctx
dense
aya expanse 32b heretic MPOA i1
C47
32B42.2 GB344 tok/s604K ctx
dense
Baichuan M2 32B Q4 K M
C47
32B42.2 GB344 tok/s604K ctx
dense
gemma 3 27b it
C47
27B38.5 GB378 tok/s731K ctx
dense
baichuan inc Baichuan M2 32B
C46
32B42.2 GB344 tok/s604K ctx
dense
👁 Cohere
Aya Expanse 8B
C46
8B25.7 GB112 tok/s8K ctx
dense
👁 Stability AI
StableLM 2 12B
C46
12B39.7 GB168 tok/s4K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
C46
24B36.4 GB336 tok/s833K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C46
24B36.4 GB336 tok/s833K ctx
dense
Mistral Small 24B Instruct 2501
C46
24B36.4 GB336 tok/s833K ctx
dense
👁 Google
Gemma 3 1B
C46
1B19.9 GB14 tok/s33K ctx
dense
mistral small 3.1 24b instruct 2503 hf
C46
24B36.4 GB336 tok/s833K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
C46
24B36.4 GB336 tok/s833K ctx
dense
👁 LMSYS
Vicuna 7B
C46
7B31.0 GB98 tok/s4K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
C46
24B36.4 GB336 tok/s833K ctx
dense
Codestral 22B v0.1
C46
22B34.9 GB308 tok/s917K ctx
dense
Codestral 22B v0.1
C46
22B34.9 GB308 tok/s917K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C46
24B36.4 GB336 tok/s833K ctx
dense
Codestral 22B v0.1
C46
22B34.9 GB308 tok/s917K ctx
dense
👁 Teknium
OpenHermes 2.5 7B
C46
7B25.1 GB98 tok/s8K ctx
dense
Codestral 22B v0.1 IMat
C46
22B34.9 GB308 tok/s917K ctx
dense
8B25.7 GB112 tok/s33K ctx
dense
Codestral 22B v0.1 i1
C45
22B34.9 GB308 tok/s917K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
C45
14B29.1 GB196 tok/s1488K ctx
dense
Codestral 21B Pruned i1
C45
21B34.2 GB294 tok/s964K ctx
dense
internlm2 5 20b chat
C45
20B33.4 GB280 tok/s1016K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
C45
7B25.1 GB98 tok/s33K ctx
dense
internlm2 limarp chat 20b
C45
20B33.4 GB280 tok/s1016K ctx
dense
internlm2 math plus 20b i1
C45
20B33.4 GB280 tok/s1016K ctx
dense
👁 Google
Gemma 2 2B
C45
2B21.7 GB28 tok/s8K ctx
dense
Phi 4 reasoning vision 15B
C45
15B29.8 GB210 tok/s1383K ctx
dense
StarCoder2 15B
C45
15B29.8 GB210 tok/s1383K ctx
dense
👁 Unsloth
Qwen3.5 9B
C45
9B25.4 GB126 tok/s2361K ctx
dense
gemma 3 12b it
C45
12B27.6 GB168 tok/s1750K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C45
9B25.4 GB126 tok/s2361K ctx
dense
Codestral RAG 19B Pruned i1
C45
19B32.7 GB266 tok/s1074K ctx
dense
NousResearch Hermes 4 14B
C45
14B29.1 GB196 tok/s1488K ctx
dense
👁 UC Berkeley
Starling LM 7B
C45
7B25.1 GB98 tok/s8K ctx
dense
Meta Llama 3.1 8B Instruct
C45
8B24.7 GB112 tok/s2666K ctx
dense
Qwen3.5 9B
C45
9B25.4 GB126 tok/s2361K ctx
dense
llava llama 3 8b v1 1
C45
8B24.7 GB112 tok/s2666K ctx
dense
starcoder2 15b instruct v0.1
C45
15B29.8 GB210 tok/s1383K ctx
dense
starcoder2 15b i1
C45
15B29.8 GB210 tok/s1383K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
C45
8B24.7 GB112 tok/s2666K ctx
dense
starcoder2 15b instruct v0.1
C45
15B29.8 GB210 tok/s1383K ctx
dense
Llama 2 7B Chat
C45
7B24.0 GB98 tok/s3059K ctx
dense
Meta Llama 3 8B Instruct
C45
8B24.7 GB112 tok/s2666K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C45
0.5B19.4 GB7 tok/s131K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
C45
8B24.7 GB112 tok/s2666K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
C45
14B29.1 GB196 tok/s1488K ctx
dense
Mistral 7B Instruct v0.2
C45
7B24.0 GB98 tok/s3059K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C45
10.7B26.7 GB150 tok/s1972K ctx
dense
Dolphin3.0 Llama3.1 8B
C45
8B24.7 GB112 tok/s2666K ctx
dense
Llama 3 8B Instruct 32k v0.1
C45
8B24.7 GB112 tok/s2666K ctx
dense
Meta Llama 3.1 8B Instruct
C45
8B24.7 GB112 tok/s2666K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C45
10.7B26.7 GB150 tok/s1972K ctx
dense
vntl llama3 8b v2
C45
8B24.7 GB112 tok/s2666K ctx
dense
HelpingAI 15B i1
C45
15B29.8 GB210 tok/s1383K ctx
dense
Mistral 7B Instruct v0.3
C45
7B24.0 GB98 tok/s3059K ctx
dense
Yi Coder 9B Chat
C45
9B25.4 GB126 tok/s2361K ctx
dense
internlm JanusCoder 14B
C45
14B29.1 GB196 tok/s1488K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C45
8B24.7 GB112 tok/s2666K ctx
dense
glm 4 9b chat 1m
C45
9B25.4 GB126 tok/s2361K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
C45
14B29.1 GB196 tok/s1488K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C45
8B24.7 GB112 tok/s2666K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C45
8B24.7 GB112 tok/s2666K ctx
dense
Hermes 3 Llama 3.1 8B
C45
8B24.7 GB112 tok/s2666K ctx
dense
Yi 1.5 9B Chat
C45
9B25.4 GB126 tok/s2361K ctx
dense
Hermes 2 Pro Llama 3 8B
C45
8B24.7 GB112 tok/s2666K ctx
dense
Dolphin3.0 Llama3.1 8B
C45
8B24.7 GB112 tok/s2666K ctx
dense
Mistral 7B Instruct v0.3
C45
7B24.0 GB98 tok/s3059K ctx
dense
granite 8b code instruct 4k
C45
8B24.7 GB112 tok/s2666K ctx
dense
Hermes 2 Pro Mistral 7B
C45
7B24.0 GB98 tok/s3059K ctx
dense
dolphin 2.9.4 llama3.1 8b
C45
8B24.7 GB112 tok/s2666K ctx
dense
solar finalised finetuned Model 10.7B i1
C45
10.7B26.7 GB150 tok/s1972K ctx
dense
zephyr 7B beta
C45
7B24.0 GB98 tok/s3059K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C45
7B24.0 GB98 tok/s3059K ctx
dense
SOLAR 10.7B v1.0
C45
10.7B26.7 GB150 tok/s1972K ctx
dense
openchat 3.6 8b 20240522 IMat
C45
8B24.7 GB112 tok/s2666K ctx
dense
Falcon H1R 7B
C45
7B24.0 GB98 tok/s3059K ctx
dense
aya expanse 8b
C45
8B24.7 GB112 tok/s2666K ctx
dense
EXAONE 3.5 7.8B Instruct
C45
7.8B24.6 GB109 tok/s2737K ctx
dense
falcon mamba 7b instruct Q4 K M
C45
7B24.0 GB98 tok/s3059K ctx
dense
dolphin v2 8b abliterated i1
C45
8B24.7 GB112 tok/s2666K ctx
dense
zephyr 7B alpha
C45
7B24.0 GB98 tok/s3059K ctx
dense
EXAONE 3.5 7.8B Instruct
C45
7.8B24.6 GB109 tok/s2737K ctx
dense
speechless zephyr code functionary 7b
C45
7B24.0 GB98 tok/s3059K ctx
dense
Yi 9B Coder i1
C45
9B25.4 GB126 tok/s2361K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C45
7.8B24.6 GB109 tok/s2737K ctx
dense
StarCoder2 7B
C45
7B24.0 GB98 tok/s3059K ctx
dense
aya expanse 8b orthogonal heretic i1
C45
8B24.7 GB112 tok/s2666K ctx
dense
exaone 3.0 7.8b it
C45
7.8B24.6 GB109 tok/s2737K ctx
dense
japanese stablelm instruct gamma 7B
C44
7B24.0 GB98 tok/s3059K ctx
dense
HelpingAI2 9B
C44
9B25.4 GB126 tok/s2361K ctx
dense
HelpingAI2.5 10B i1
C44
10B26.2 GB140 tok/s2116K ctx
dense
Falcon H1 7B Instruct
C44
7B24.0 GB98 tok/s3059K ctx
dense
👁 Unsloth
Falcon H1R 7B
C44
7B24.0 GB98 tok/s3059K ctx
dense
Yi 1.5 6B Chat
C44
6B23.3 GB84 tok/s3583K ctx
dense
Helply 10.2b chat i1
C44
10.2B26.3 GB143 tok/s2073K ctx
dense
aya expanse 8b orthogonal heretic
C44
8B24.7 GB112 tok/s2666K ctx
dense
HelpingAI2 9B i1
C44
9B25.4 GB126 tok/s2361K ctx
dense
HelpingAI 9B 200k i1
C44
9B25.4 GB126 tok/s2361K ctx
dense
stablelm 2 zephyr 1 6b
C44
6B23.3 GB84 tok/s3583K ctx
dense
HelpingAI 9B i1
C44
9B25.4 GB126 tok/s2361K ctx
dense
Mamba Codestral 7B v0.1
C44
7B24.0 GB98 tok/s3059K ctx
dense
stabilityai japanese stablelm base gamma 7b
C44
7B24.0 GB98 tok/s3059K ctx
dense
baichuan2 7b chat
C44
7B24.0 GB98 tok/s3059K ctx
dense
internlm2 5 1 8b chat i1
C44
8B24.7 GB112 tok/s2666K ctx
dense
DiscoPOP zephyr 7b gemma
C44
7B24.0 GB98 tok/s3059K ctx
dense
internlm3 8b instruct abliterated i1
C44
8B24.7 GB112 tok/s2666K ctx
dense
starcoder2 7b
C44
7B24.0 GB98 tok/s3059K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C44
7B24.0 GB98 tok/s3059K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C44
7B24.0 GB98 tok/s3059K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C44
7B24.0 GB98 tok/s3059K ctx
dense
internlm2 math plus 7b IMat
C44
7B24.0 GB98 tok/s3059K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C44
7B24.0 GB98 tok/s3059K ctx
dense
internlm2 5 7b chat i1
C44
7B24.0 GB98 tok/s3059K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C44
7B24.0 GB98 tok/s3059K ctx
dense
MD Judge v0 2 internlm2 7b i1
C44
7B24.0 GB98 tok/s3059K ctx
dense
Yi 1.5 6B Chat
C44
6B23.3 GB84 tok/s3583K ctx
dense
👁 01.AI
Yi 1.5 6B
C44
6B23.5 GB84 tok/s4K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C44
7B24.0 GB98 tok/s3059K ctx
dense
stablelm 2 1 6b chat imatrix
C44
6B23.3 GB84 tok/s3583K ctx
dense
jointpreferences mistral 7b sft helpful
C44
7B24.0 GB98 tok/s3059K ctx
dense
zephyr 7b dpo full i1
C44
7B24.0 GB98 tok/s3059K ctx
dense
blossom v3 baichuan2 7b i1
C44
7B24.0 GB98 tok/s3059K ctx
dense
blossom v1 baichuan 7b i1
C44
7B24.0 GB98 tok/s3059K ctx
dense
👁 Intel
Neural Chat 7B
C44
7B25.1 GB98 tok/s8K ctx
dense
HelpingAI2 6B
C44
6B23.3 GB84 tok/s3583K ctx
dense
👁 BigCode
StarCoder2 7B
C44
7B23.7 GB98 tok/s16K ctx
dense
HelpingAI2 6B i1
C44
6B23.3 GB84 tok/s3583K ctx
dense
👁 DeepSeek
DeepSeek LLM 7B
C44
7B30.5 GB98 tok/s4K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
C44
4B23.3 GB56 tok/s4K ctx
dense
HelpingAI2.5 5B i1
C43
5B22.5 GB70 tok/s4316K ctx
dense
👁 Unsloth
Qwen3.5 4B
C43
4B21.8 GB56 tok/s5416K ctx
dense
gemma 3 4b it
C43
4B21.8 GB56 tok/s5416K ctx
dense
gemma 3 4b it
C43
4B21.8 GB56 tok/s5416K ctx
dense
👁 Alibaba
Qwen 3 0.6B
C43
0.6B20.1 GB8 tok/s33K ctx
dense
👁 Meta
Llama 3.2 1B
C43
1B20.0 GB14 tok/s128K ctx
dense
Llama 3.2 3B Instruct
C42
3B21.4 GB42 tok/s7234K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C42
3B21.1 GB42 tok/s7249K ctx
dense
Llama 3.2 3B Instruct
C42
3B21.1 GB42 tok/s7249K ctx
dense
Ministral 3 3B Instruct 2512
C42
3B21.1 GB42 tok/s7249K ctx
dense
HELVETE 3B
C42
3B21.1 GB42 tok/s7249K ctx
dense
Hermes 3 Llama 3.2 3B
C42
3B21.1 GB42 tok/s7249K ctx
dense
stablelm zephyr 3b
C42
3B21.1 GB42 tok/s7249K ctx
dense
StarCoder2 3B
C42
3B21.1 GB42 tok/s7249K ctx
dense
AI21 Jamba Reasoning 3B
C42
3B21.1 GB42 tok/s7249K ctx
dense
stablelm 3b 4e1t
C41
3B21.1 GB42 tok/s7249K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C41
3B21.1 GB42 tok/s7249K ctx
dense
ai21labs AI21 Jamba2 3B
C41
3B21.1 GB42 tok/s7249K ctx
dense
HelpingAI 3B hindi i1
C41
3B21.1 GB42 tok/s7249K ctx
dense
AI21 Jamba2 3B
C41
3B21.1 GB42 tok/s7249K ctx
dense
HelpingAI 3B hindi
C41
3B21.1 GB42 tok/s7249K ctx
dense
AI21 Jamba2 3B i1
C41
3B21.1 GB42 tok/s7249K ctx
dense
EXAONE 3.5 2.4B Instruct
C41
2.4B20.6 GB34 tok/s9082K ctx
dense
gemma 2 2b it
C41
2B20.8 GB28 tok/s10886K ctx
dense
👁 Google
gemma 2b
C41
2B20.4 GB28 tok/s10914K ctx
dense
Gemmasutra Mini 2B v1
C41
2B20.4 GB28 tok/s10914K ctx
dense
K EXAONE 236B A23B
C41
236B190.5 GB36 tok/s10K ctx
dense
👁 Alibaba
Qwen 3.5 0.6B
C41
0.6B20.1 GB8 tok/s131K ctx
dense
gemma 2 2b it
C41
2B20.4 GB28 tok/s10914K ctx
dense
Baichuan M3 235B
C41
235B189.8 GB37 tok/s10K ctx
dense
Baichuan M3 235B i1
C41
235B189.8 GB37 tok/s10K ctx
dense
👁 BigCode
StarCoder2 3B
C40
3B21.2 GB42 tok/s16K ctx
dense
F

F Tier -- Can't Run (38 models)

Too heavy for this hardware.

👁 Qwen
Qwen2.5 1.5B Instruct
D40
1.5B20.0 GB21 tok/s14580K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B
D40
1.5B20.0 GB21 tok/s14580K ctx
dense
Yi Coder 1.5B Chat
D40
1.5B20.0 GB21 tok/s14580K ctx
dense
stablelm 2 zephyr 1.6b
D39
1.6B20.1 GB22 tok/s13664K ctx
dense
logos16v2 stablelm2 1.6b i1
D39
1.6B20.1 GB22 tok/s13664K ctx
dense
Yi Coder 1.5B
D39
1.5B20.0 GB21 tok/s14580K ctx
dense
👁 Unsloth
Falcon H1 1.5B Instruct
D39
1.5B20.0 GB21 tok/s14580K ctx
dense
TinyLlama 1.1B Chat v1.0
D39
1.1B19.7 GB15 tok/s19913K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
D39
0.5B19.4 GB7 tok/s131K ctx
dense
EXAONE 4.0 1.2B
D39
1.2B19.8 GB17 tok/s18246K ctx
dense
Llama 3.2 1B Instruct Q8 0
D39
1B19.8 GB14 tok/s21884K ctx
dense
TinyLlama 1.1B Chat v0.3
D38
1.1B19.7 GB15 tok/s19913K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
D38
1.1B19.7 GB15 tok/s19913K ctx
dense
Llama 3.2 1B Instruct
D38
1B19.6 GB14 tok/s21912K ctx
dense
gemma 3 1b it
D38
1B19.6 GB14 tok/s21912K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
D38
1.1B19.7 GB15 tok/s19913K ctx
dense
Falcon3 1B Instruct abliterated
D38
1B19.6 GB14 tok/s21912K ctx
dense
SmolVLM 500M Instruct
D36
0.5B19.4 GB7 tok/s25710K ctx
dense
embeddinggemma 300M
D35
0.3B19.2 GB4 tok/s25737K ctx
dense
granite embedding 107m multilingual
D33
0.11B19.1 GB2 tok/s25766K ctx
dense
Falcon H1 Tiny 90M Instruct
D33
0.09B19.1 GB2 tok/s25767K ctx
dense
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B314.6 GB24 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B263.9 GB41 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B436.0 GB10 tok/s4K ctx
+1moe
F0
744B491.8 GB7 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B497.9 GB7 tok/s4K ctx
moe
F0
1000B636.3 GB6 tok/s4K ctx
moe
F0
1000B636.3 GB6 tok/s4K ctx
+1moe
👁 DeepSeek
DeepSeek V3 671B
F0
671B487.8 GB8 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B487.8 GB8 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B882.8 GB4 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B487.8 GB8 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B221.5 GB76 tok/s5K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B221.5 GB76 tok/s5K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B265.8 GB40 tok/s4K ctx
moe
👁 Meta
Llama 3.1 405B
F0
405B273.6 GB13 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B428.7 GB11 tok/s4K ctx
moe
👁 Unsloth
Qwen3.5 397B A17B
F0
397B307.6 GB10 tok/s4K ctx
dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

H100 NVL 188GB

188 GB VRAM

View tier list

AMD Instinct MI300X 192GB

192 GB VRAM

View tier list

NVIDIA GB200 192GB

192 GB VRAM

View tier list

B100 192GB

192 GB VRAM

View tier list
Full NVIDIA B200 180GB pageCompare this hardware