NVIDIA A100 80GB

70B59.8 GB40 tok/s55K ctx

Solar Open 69B REAP i1

69B59.1 GB41 tok/s57K ctx

stabilityai japanese stablelm instruct beta 70b

70B59.8 GB40 tok/s55K ctx

BaichuanMed OCR 72B i1

72B61.3 GB39 tok/s52K ctx

Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored

👁 01.AI
Yi 34B Chat

C52

34B33.3 GB90 tok/s200K ctx

dense

C52

48B43.8 GB59 tok/s119K ctx

35B34.4 GB80 tok/s194K ctx

👁 Unsloth
Qwen3.5 35B A3B

C51

35B34.4 GB80 tok/s194K ctx

dense

Qwen3.5 35B A3B

C51

36B35.1 GB78 tok/s186K ctx

👁 IBM
Granite 3.1 8B

C51

8B15.7 GB112 tok/s128K ctx

state-space

Hermes 4.3 36B

C51

👁 DeepSeek
DeepSeek R1 1.5B

C51

1.5B10.2 GB21 tok/s33K ctx

dense

👁 01.AI
Yi 1.5 9B

C51

9B15.9 GB126 tok/s4K ctx

dense

👁 HuggingFace
SmolLM3 3B

C51

3B12.7 GB42 tok/s128K ctx

dense

👁 TinyLlama
TinyLlama 1.1B

C50

1.1B9.9 GB15 tok/s4K ctx

dense

EXAONE 4.0 32B

aya expanse 32b heretic MPOA i1

Baichuan M2 32B Q4 K M

baichuan inc Baichuan M2 32B

👁 Unsloth
Qwen3.5 27B

C50

27B28.5 GB104 tok/s276K ctx

dense

👁 Alibaba
Qwen 2.5 Math 7B

C50

7B14.0 GB98 tok/s4K ctx

dense

👁 Unsloth
gemma 3 27b it

C50

27B28.5 GB104 tok/s276K ctx

dense

👁 Stability AI
StableLM 2 12B

C50

12B29.7 GB152 tok/s4K ctx

dense

gemma 3 27b it

27B28.5 GB104 tok/s276K ctx

👁 Unsloth
Qwen3.5 122B A10B

C50

122B83.0 GB21 tok/s13K ctx

dense

Solar Open 100B

100B81.6 GB23 tok/s14K ctx

Solar Open 100B i1

100B81.6 GB23 tok/s14K ctx

cognitivecomputations Dolphin Mistral 24B Venice Edition

👁 Unsloth
Mistral Small 3.2 24B Instruct 2506

C49

24B26.4 GB117 tok/s321K ctx

dense

Mistral Small 24B Instruct 2501

mistral small 3.1 24b instruct 2503 hf

cognitivecomputations Dolphin3.0 R1 Mistral 24B

Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1

cognitivecomputations Dolphin Mistral 24B Venice Edition

👁 BigCode
StarCoder2 15B

C49

15B20.9 GB177 tok/s16K ctx

dense

Codestral 22B v0.1

Codestral 22B v0.1

Codestral 22B v0.1

Codestral 22B v0.1 IMat

👁 LMSYS
Vicuna 7B

C48

7B21.0 GB98 tok/s4K ctx

dense

👁 Alibaba
Qwen 2.5 1.5B

C48

1.5B10.2 GB21 tok/s131K ctx

dense

Codestral 22B v0.1 i1

👁 OpenChat
OpenChat 7B

C48

7B15.1 GB98 tok/s8K ctx

dense

Codestral 21B Pruned i1

21B24.2 GB134 tok/s379K ctx

internlm2 5 20b chat

20B23.4 GB140 tok/s402K ctx

internlm2 limarp chat 20b

20B23.4 GB140 tok/s402K ctx

internlm2 math plus 20b i1

20B23.4 GB140 tok/s402K ctx

Codestral RAG 19B Pruned i1

👁 Cohere
Aya Expanse 8B

C48

8B15.7 GB112 tok/s8K ctx

dense

19B22.7 GB148 tok/s428K ctx

Phi 4 reasoning vision 15B

👁 Unsloth
DeepSeek R1 Distill Qwen 14B

C47

14B19.1 GB196 tok/s610K ctx

dense

StarCoder2 15B

NousResearch Hermes 4 14B

starcoder2 15b instruct v0.1

starcoder2 15b i1

starcoder2 15b instruct v0.1

👁 Cognitive Computations
Dolphin 2.9 8B

C47

8B15.7 GB112 tok/s33K ctx

dense

HelpingAI 15B i1

👁 Teknium
OpenHermes 2.5 7B

C47

7B15.1 GB98 tok/s8K ctx

dense

gemma 3 12b it

12B17.6 GB168 tok/s726K ctx

GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV

internlm JanusCoder 14B

GGUF SOLARized GraniStral 14B 1902 YeAM HCT

Qwen3.5 9B Uncensored HauhauCS Aggressive

👁 Google
Gemma 3 1B

C46

1B9.9 GB14 tok/s33K ctx

dense

👁 Hugging Face H4
Zephyr 7B Beta

C46

7B15.1 GB98 tok/s33K ctx

dense

👁 Unsloth
Qwen3.5 9B

C46

9B15.4 GB126 tok/s995K ctx

dense

SOLAR 10.7B Instruct v1.0 uncensored

Nous Hermes 2 SOLAR 10.7B

Qwen3.5 9B

Meta Llama 3.1 8B Instruct

👁 UC Berkeley
Starling LM 7B

C46

7B15.1 GB98 tok/s8K ctx

dense

llava llama 3 8b v1 1

👁 Unsloth
DeepSeek R1 0528 Qwen3 8B

C46

8B14.7 GB112 tok/s1130K ctx

dense

Yi Coder 9B Chat

glm 4 9b chat 1m

Meta Llama 3 8B Instruct

solar finalised finetuned Model 10.7B i1

👁 Unsloth
DeepSeek R1 Distill Llama 8B

C46

8B14.7 GB112 tok/s1130K ctx

dense

Dolphin3.0 Llama3.1 8B

Llama 3 8B Instruct 32k v0.1

Meta Llama 3.1 8B Instruct

vntl llama3 8b v2

SOLAR 10.7B v1.0

DeepSeek R1 0528 Qwen3 8B

Llama 2 7B Chat

Mistral 7B Instruct v0.2

Yi 1.5 9B Chat

DeepSeek R1 0528 Qwen3 8B

👁 Google
Gemma 2 2B

C46

2B11.7 GB28 tok/s8K ctx

dense

Mistral 7B Instruct v0.3

Qwen3 8B DeepSeek v3.2 Speciale Distill

Hermes 3 Llama 3.1 8B

Hermes 2 Pro Llama 3 8B

Dolphin3.0 Llama3.1 8B

granite 8b code instruct 4k

👁 DeepSeek
DeepSeek LLM 7B

C46

7B20.5 GB98 tok/s4K ctx

dense

dolphin 2.9.4 llama3.1 8b

HelpingAI2.5 10B i1

10B16.2 GB140 tok/s887K ctx

Helply 10.2b chat i1

10.2B16.3 GB143 tok/s868K ctx

Yi 9B Coder i1

openchat 3.6 8b 20240522 IMat

Mistral 7B Instruct v0.3

Hermes 2 Pro Mistral 7B

aya expanse 8b

EXAONE 3.5 7.8B Instruct

HelpingAI2 9B

zephyr 7B beta

dolphin v2 8b abliterated i1

Nous Hermes 2 Mistral 7B DPO

EXAONE 3.5 7.8B Instruct

EXAONE 3.5 7.8B Instruct i1

HelpingAI2 9B i1

aya expanse 8b orthogonal heretic i1

Falcon H1R 7B

HelpingAI 9B 200k i1

exaone 3.0 7.8b it

falcon mamba 7b instruct Q4 K M

HelpingAI 9B i1

zephyr 7B alpha

speechless zephyr code functionary 7b

StarCoder2 7B

aya expanse 8b orthogonal heretic

japanese stablelm instruct gamma 7B

Falcon H1 7B Instruct

👁 Unsloth
Falcon H1R 7B

C45

7B14.0 GB98 tok/s1304K ctx

dense

internlm2 5 1 8b chat i1

internlm3 8b instruct abliterated i1

Mamba Codestral 7B v0.1

Yi 1.5 6B Chat

stabilityai japanese stablelm base gamma 7b

baichuan2 7b chat

👁 Alibaba
Qwen 2.5 Coder 0.5B

C45

0.5B9.4 GB7 tok/s131K ctx

dense

DiscoPOP zephyr 7b gemma

starcoder2 7b

👁 Intel
Neural Chat 7B

C45

7B15.1 GB98 tok/s8K ctx

dense

stablelm 2 zephyr 1 6b

zephyr 7b beta Mistral 7B Instruct v0.2

OpenChat 3.5 7B Qwen v2.0 i1

OpenChat 3.5 7B Starling v2.0 i1

internlm2 math plus 7b IMat

CodeNinja 1.0 OpenChat 7B i1

internlm2 5 7b chat i1

OpenSafetyLab MD Judge v0 2 internlm2 7b

MD Judge v0 2 internlm2 7b i1

zephyr 7b gemma sft african ultrachat 100k

jointpreferences mistral 7b sft helpful

zephyr 7b dpo full i1

blossom v3 baichuan2 7b i1

blossom v1 baichuan 7b i1

👁 01.AI
Yi 1.5 6B

C45

6B13.5 GB84 tok/s4K ctx

dense

Yi 1.5 6B Chat

stablelm 2 1 6b chat imatrix

👁 BigCode
StarCoder2 7B

C45

7B13.7 GB98 tok/s16K ctx

dense

HelpingAI2 6B

HelpingAI2 6B i1

5B12.5 GB70 tok/s1858K ctx

👁 NVIDIA
Nemotron Mini 4B

C45

4B13.3 GB56 tok/s4K ctx

dense

HelpingAI2.5 5B i1

C44

4B11.8 GB56 tok/s2344K ctx

👁 Unsloth
Qwen3.5 4B

C44

4B11.8 GB56 tok/s2344K ctx

dense

gemma 3 4b it

C44

4B11.8 GB56 tok/s2344K ctx

gemma 3 4b it

C44

3B11.4 GB42 tok/s3138K ctx

👁 Alibaba
Qwen 3 0.6B

C43

0.6B10.1 GB8 tok/s33K ctx

dense

👁 Meta
Llama 3.2 1B

C43

1B10.0 GB14 tok/s128K ctx

dense

Llama 3.2 3B Instruct

C43

👁 Qwen
Qwen2.5 3B Instruct

C43

3B11.1 GB42 tok/s3153K ctx

dense

Llama 3.2 3B Instruct

Ministral 3 3B Instruct 2512

HELVETE 3B

Hermes 3 Llama 3.2 3B

stablelm zephyr 3b

StarCoder2 3B

AI21 Jamba Reasoning 3B

stablelm 3b 4e1t

ai21labs AI21 Jamba Reasoning 3B

ai21labs AI21 Jamba2 3B

HelpingAI 3B hindi i1

AI21 Jamba2 3B

HelpingAI 3B hindi

AI21 Jamba2 3B i1

gemma 2 2b it

2B10.8 GB28 tok/s4742K ctx

EXAONE 3.5 2.4B Instruct

2.4B10.6 GB34 tok/s3962K ctx

👁 Google
gemma 2b

C41

2B10.4 GB28 tok/s4770K ctx

dense

Gemmasutra Mini 2B v1

2B10.4 GB28 tok/s4770K ctx

gemma 2 2b it

2B10.4 GB28 tok/s4770K ctx

👁 Alibaba
Qwen 3.5 0.6B

C41

0.6B10.1 GB8 tok/s131K ctx

dense

👁 BigCode
StarCoder2 3B

C41

3B11.2 GB42 tok/s16K ctx

dense

👁 Qwen
Qwen2.5 1.5B Instruct

C40

1.5B10.0 GB21 tok/s6388K ctx

dense

F Tier -- Can't Run (44 models)

Too heavy for this hardware.

👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B

D40

1.5B10.0 GB21 tok/s6388K ctx

dense

Yi Coder 1.5B Chat

1.5B10.0 GB21 tok/s6388K ctx

stablelm 2 zephyr 1.6b

1.6B10.1 GB22 tok/s5984K ctx

logos16v2 stablelm2 1.6b i1

1.6B10.1 GB22 tok/s5984K ctx

Yi Coder 1.5B

1.5B10.0 GB21 tok/s6388K ctx

👁 Unsloth
Falcon H1 1.5B Instruct

D39

1.5B10.0 GB21 tok/s6388K ctx

dense

TinyLlama 1.1B Chat v1.0

1.1B9.7 GB15 tok/s8742K ctx

👁 Alibaba
Qwen 2.5 0.5B

D39

0.5B9.4 GB7 tok/s131K ctx

dense

EXAONE 4.0 1.2B

1.2B9.8 GB17 tok/s8006K ctx

Llama 3.2 1B Instruct Q8 0

1B9.8 GB14 tok/s9596K ctx

TinyLlama 1.1B Chat v0.3

1.1B9.7 GB15 tok/s8742K ctx

👁 TinyLlama
TinyLlama 1.1B Chat v0.6

D39

1.1B9.7 GB15 tok/s8742K ctx

dense

Llama 3.2 1B Instruct

1B9.6 GB14 tok/s9624K ctx

gemma 3 1b it

1B9.6 GB14 tok/s9624K ctx

TinyLlama 1.1B Chat v1.0 imatrix

D38

1.1B9.7 GB15 tok/s8742K ctx

Falcon3 1B Instruct abliterated

D38

1B9.6 GB14 tok/s9624K ctx

0.5B9.4 GB7 tok/s11310K ctx

SmolVLM 500M Instruct

D37

0.3B9.2 GB4 tok/s11337K ctx

embeddinggemma 300M

D35

granite embedding 107m multilingual

D33

0.11B9.1 GB2 tok/s11366K ctx

Falcon H1 Tiny 90M Instruct

D33

0.09B9.1 GB2 tok/s11367K ctx

230B153.0 GB12 tok/s4K ctx

👁 Alibaba
Qwen 3 235B A22B

235B155.1 GB10 tok/s4K ctx

moe

👁 Alibaba
Qwen3-Coder 480B A35B Instruct

480B304.6 GB3 tok/s4K ctx

moe

👁 Alibaba
Qwen 3.5 397B A17B

397B253.9 GB4 tok/s4K ctx

moe

👁 Mistral
Mixtral 8x22B

141B98.3 GB25 tok/s4K ctx

moe

👁 Mistral
Mistral Large 3

675B426.0 GB2 tok/s4K ctx

+1moe

👁 Z.ai
GLM-5

744B481.8 GB2 tok/s4K ctx

moe

👁 Z.ai
GLM-5.1

754B487.9 GB2 tok/s4K ctx

moe

👁 Moonshot AI
Kimi K2.5

1000B626.3 GB2 tok/s4K ctx

moe

👁 Moonshot AI
Kimi K2.6

1000B626.3 GB2 tok/s4K ctx

+1moe

👁 DeepSeek
DeepSeek V3 671B

671B477.8 GB2 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V3.1 671B

671B477.8 GB2 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V4 Pro

1600B872.8 GB2 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V4 Flash

284B168.2 GB9 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek R1 671B

671B477.8 GB2 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek Coder V2 236B

236B211.5 GB6 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V2.5 236B

236B211.5 GB6 tok/s4K ctx

moe

👁 Meta
Llama 4 Maverick 17B 128E

400B255.8 GB3 tok/s4K ctx

moe

👁 Meta
Llama 3.1 405B

405B263.6 GB2 tok/s4K ctx

dense

👁 DeepSeek
DeepSeek V3.2

671B418.7 GB2 tok/s4K ctx

moe

MiniMax M2.7

moe

K EXAONE 236B A23B

236B180.5 GB3 tok/s4K ctx

235B179.8 GB3 tok/s4K ctx

Baichuan M3 235B

235B179.8 GB3 tok/s4K ctx

Baichuan M3 235B i1

👁 Unsloth
Qwen3.5 397B A17B

397B297.6 GB2 tok/s4K ctx

dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

NVIDIA H100 80GB

80 GB VRAM

NVIDIA A800 80GB

80 GB VRAM

NVIDIA H800 80GB

80 GB VRAM

NVIDIA H100 PCIe 80GB

80 GB VRAM