AMD Instinct MI300X 192GB

100B92.8 GB68 tok/s151K ctx

Solar Open 100B i1

C51

👁 DeepSeek
DeepSeek R1 1.5B

C50

1.5B21.4 GB21 tok/s33K ctx

dense

👁 TinyLlama
TinyLlama 1.1B

C50

1.1B21.1 GB15 tok/s4K ctx

dense

Llama 3.3 70B Instruct

70B71.0 GB97 tok/s252K ctx

K EXAONE 236B A23B

236B191.7 GB29 tok/s16K ctx

👁 HuggingFace
SmolLM3 3B

C50

3B23.9 GB42 tok/s128K ctx

dense

Baichuan M3 235B

235B191.0 GB29 tok/s17K ctx

Baichuan M3 235B i1

235B191.0 GB29 tok/s17K ctx

69B70.3 GB98 tok/s257K ctx

👁 IBM
Granite 3.1 8B

C49

8B26.9 GB112 tok/s128K ctx

state-space

Solar Open 69B REAP i1

C49

72B72.5 GB94 tok/s243K ctx

BaichuanMed OCR 72B i1

C49

stabilityai japanese stablelm instruct beta 70b

C49

70B71.0 GB97 tok/s252K ctx

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

👁 01.AI
Yi 1.5 9B

C49

9B27.1 GB126 tok/s4K ctx

dense

👁 Alibaba
Qwen 2.5 Math 7B

C49

7B25.2 GB98 tok/s4K ctx

dense

👁 01.AI
Yi 34B Chat

C48

34B44.5 GB216 tok/s200K ctx

dense

C48

48B55.0 GB141 tok/s406K ctx

35B45.6 GB194 tok/s587K ctx

👁 Alibaba
Qwen 2.5 1.5B

C48

1.5B21.4 GB21 tok/s131K ctx

dense

👁 Unsloth
Qwen3.5 35B A3B

C47

35B45.6 GB194 tok/s587K ctx

dense

Qwen3.5 35B A3B

C47

36B46.3 GB188 tok/s569K ctx

Hermes 4.3 36B

C47

👁 BigCode
StarCoder2 15B

C47

15B32.1 GB210 tok/s16K ctx

dense

👁 OpenChat
OpenChat 7B

C47

7B26.3 GB98 tok/s8K ctx

dense

👁 Unsloth
Qwen3.5 27B

C47

27B39.7 GB251 tok/s786K ctx

dense

👁 Unsloth
gemma 3 27b it

C47

27B39.7 GB251 tok/s786K ctx

dense

EXAONE 4.0 32B

aya expanse 32b heretic MPOA i1

👁 Cohere
Aya Expanse 8B

C46

8B26.9 GB112 tok/s8K ctx

dense

Baichuan M2 32B Q4 K M

gemma 3 27b it

27B39.7 GB251 tok/s786K ctx

baichuan inc Baichuan M2 32B

cognitivecomputations Dolphin Mistral 24B Venice Edition

👁 Unsloth
Mistral Small 3.2 24B Instruct 2506

C46

24B37.6 GB282 tok/s895K ctx

dense

👁 Google
Gemma 3 1B

C46

1B21.1 GB14 tok/s33K ctx

dense

👁 Stability AI
StableLM 2 12B

C46

12B40.9 GB168 tok/s4K 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

👁 LMSYS
Vicuna 7B

C46

7B32.2 GB98 tok/s4K ctx

dense

Codestral 22B v0.1

Codestral 22B v0.1

cognitivecomputations Dolphin Mistral 24B Venice Edition

Codestral 22B v0.1

👁 Teknium
OpenHermes 2.5 7B

C46

7B26.3 GB98 tok/s8K ctx

dense

👁 Cognitive Computations
Dolphin 2.9 8B

C46

8B26.9 GB112 tok/s33K ctx

dense

Codestral 22B v0.1 IMat

👁 Unsloth
DeepSeek R1 Distill Qwen 14B

C45

14B30.3 GB196 tok/s1593K ctx

dense

👁 Hugging Face H4
Zephyr 7B Beta

C45

7B26.3 GB98 tok/s33K ctx

dense

Codestral 22B v0.1 i1

internlm2 5 20b chat

20B34.6 GB280 tok/s1090K ctx

Codestral 21B Pruned i1

21B35.4 GB294 tok/s1034K ctx

internlm2 limarp chat 20b

👁 Google
Gemma 2 2B

C45

2B22.9 GB28 tok/s8K ctx

dense

20B34.6 GB280 tok/s1090K ctx

Phi 4 reasoning vision 15B

internlm2 math plus 20b i1

20B34.6 GB280 tok/s1090K ctx

StarCoder2 15B

Qwen3.5 9B Uncensored HauhauCS Aggressive

👁 Unsloth
Qwen3.5 9B

C45

9B26.6 GB126 tok/s2525K ctx

dense

gemma 3 12b it

12B28.8 GB168 tok/s1873K ctx

NousResearch Hermes 4 14B

Codestral RAG 19B Pruned i1

19B33.9 GB266 tok/s1152K ctx

Meta Llama 3.1 8B Instruct

👁 UC Berkeley
Starling LM 7B

C45

7B26.3 GB98 tok/s8K ctx

dense

llava llama 3 8b v1 1

Qwen3.5 9B

starcoder2 15b instruct v0.1

👁 Unsloth
DeepSeek R1 0528 Qwen3 8B

C45

8B25.9 GB112 tok/s2850K ctx

dense

👁 Alibaba
Qwen 2.5 Coder 0.5B

C45

0.5B20.6 GB7 tok/s131K ctx

dense

Llama 2 7B Chat

starcoder2 15b i1

Meta Llama 3 8B Instruct

starcoder2 15b instruct v0.1

👁 Unsloth
DeepSeek R1 Distill Llama 8B

C45

8B25.9 GB112 tok/s2850K ctx

dense

Mistral 7B Instruct v0.2

Dolphin3.0 Llama3.1 8B

Llama 3 8B Instruct 32k v0.1

SOLAR 10.7B Instruct v1.0 uncensored

Meta Llama 3.1 8B Instruct

vntl llama3 8b v2

GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV

Mistral 7B Instruct v0.3

Nous Hermes 2 SOLAR 10.7B

Yi Coder 9B Chat

DeepSeek R1 0528 Qwen3 8B

glm 4 9b chat 1m

HelpingAI 15B i1

internlm JanusCoder 14B

GGUF SOLARized GraniStral 14B 1902 YeAM HCT

DeepSeek R1 0528 Qwen3 8B

Qwen3 8B DeepSeek v3.2 Speciale Distill

Hermes 3 Llama 3.1 8B

Yi 1.5 9B Chat

Hermes 2 Pro Llama 3 8B

Dolphin3.0 Llama3.1 8B

Mistral 7B Instruct v0.3

Hermes 2 Pro Mistral 7B

granite 8b code instruct 4k

dolphin 2.9.4 llama3.1 8b

zephyr 7B beta

solar finalised finetuned Model 10.7B i1

Nous Hermes 2 Mistral 7B DPO

SOLAR 10.7B v1.0

openchat 3.6 8b 20240522 IMat

Falcon H1R 7B

aya expanse 8b

EXAONE 3.5 7.8B Instruct

falcon mamba 7b instruct Q4 K M

zephyr 7B alpha

dolphin v2 8b abliterated i1

speechless zephyr code functionary 7b

EXAONE 3.5 7.8B Instruct

Yi 9B Coder i1

EXAONE 3.5 7.8B Instruct i1

StarCoder2 7B

aya expanse 8b orthogonal heretic i1

exaone 3.0 7.8b it

japanese stablelm instruct gamma 7B

Falcon H1 7B Instruct

HelpingAI2 9B

👁 Unsloth
Falcon H1R 7B

C44

7B25.2 GB98 tok/s3270K ctx

dense

Yi 1.5 6B Chat

HelpingAI2.5 10B i1

10B27.4 GB140 tok/s2264K ctx

Helply 10.2b chat i1

10.2B27.5 GB143 tok/s2218K ctx

aya expanse 8b orthogonal heretic

HelpingAI2 9B i1

HelpingAI 9B 200k i1

stablelm 2 zephyr 1 6b

Mamba Codestral 7B v0.1

stabilityai japanese stablelm base gamma 7b

HelpingAI 9B i1

baichuan2 7b chat

DiscoPOP zephyr 7b gemma

internlm2 5 1 8b chat i1

internlm3 8b instruct abliterated i1

starcoder2 7b

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

Yi 1.5 6B Chat

stablelm 2 1 6b chat imatrix

👁 01.AI
Yi 1.5 6B

C44

6B24.7 GB84 tok/s4K ctx

dense

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

👁 Intel
Neural Chat 7B

C44

7B26.3 GB98 tok/s8K ctx

dense

HelpingAI2 6B

👁 BigCode
StarCoder2 7B

C44

7B24.9 GB98 tok/s16K ctx

dense

HelpingAI2 6B i1

5B23.7 GB70 tok/s4611K ctx

👁 NVIDIA
Nemotron Mini 4B

C44

4B24.5 GB56 tok/s4K ctx

dense

👁 DeepSeek
DeepSeek LLM 7B

C44

7B31.7 GB98 tok/s4K ctx

dense

HelpingAI2.5 5B i1

C43

4B23.0 GB56 tok/s5784K ctx

👁 Unsloth
Qwen3.5 4B

C43

4B23.0 GB56 tok/s5784K ctx

dense

gemma 3 4b it

C43

4B23.0 GB56 tok/s5784K ctx

gemma 3 4b it

C43

👁 Alibaba
Qwen 3 0.6B

C43

0.6B21.3 GB8 tok/s33K ctx

dense

👁 Meta
Llama 3.2 1B

C43

1B21.2 GB14 tok/s128K ctx

dense

Llama 3.2 3B Instruct

3B22.6 GB42 tok/s7725K ctx

👁 Qwen
Qwen2.5 3B Instruct

C42

3B22.3 GB42 tok/s7740K 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

EXAONE 3.5 2.4B Instruct

2.4B21.8 GB34 tok/s9696K ctx

gemma 2 2b it

2B22.0 GB28 tok/s11623K ctx

👁 Google
gemma 2b

C41

2B21.6 GB28 tok/s11652K ctx

dense

Gemmasutra Mini 2B v1

2B21.6 GB28 tok/s11652K ctx

👁 Alibaba
Qwen 3.5 0.6B

C41

0.6B21.3 GB8 tok/s131K ctx

dense

gemma 2 2b it

2B21.6 GB28 tok/s11652K ctx

1.5B21.2 GB21 tok/s15563K ctx

👁 BigCode
StarCoder2 3B

C40

3B22.4 GB42 tok/s16K ctx

dense

F Tier -- Can't Run (36 models)

Too heavy for this hardware.

👁 Qwen
Qwen2.5 1.5B Instruct

D40

1.5B21.2 GB21 tok/s15563K ctx

dense

👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B

D40

1.5B21.2 GB21 tok/s15563K ctx

dense

Yi Coder 1.5B Chat

D40

stablelm 2 zephyr 1.6b

1.6B21.3 GB22 tok/s14586K ctx

logos16v2 stablelm2 1.6b i1

1.6B21.3 GB22 tok/s14586K ctx

Yi Coder 1.5B

1.5B21.2 GB21 tok/s15563K ctx

👁 Unsloth
Falcon H1 1.5B Instruct

D39

1.5B21.2 GB21 tok/s15563K ctx

dense

TinyLlama 1.1B Chat v1.0

1.1B20.9 GB15 tok/s21253K ctx

👁 Alibaba
Qwen 2.5 0.5B

D39

0.5B20.6 GB7 tok/s131K ctx

dense

EXAONE 4.0 1.2B

1.2B21.0 GB17 tok/s19475K ctx

Llama 3.2 1B Instruct Q8 0

1B21.0 GB14 tok/s23358K ctx

TinyLlama 1.1B Chat v0.3

1.1B20.9 GB15 tok/s21253K ctx

👁 TinyLlama
TinyLlama 1.1B Chat v0.6

D38

1.1B20.9 GB15 tok/s21253K ctx

dense

Llama 3.2 1B Instruct

1B20.8 GB14 tok/s23387K ctx

gemma 3 1b it

1B20.8 GB14 tok/s23387K ctx

TinyLlama 1.1B Chat v1.0 imatrix

1.1B20.9 GB15 tok/s21253K ctx

Falcon3 1B Instruct abliterated

1B20.8 GB14 tok/s23387K ctx

0.5B20.6 GB7 tok/s27438K ctx

SmolVLM 500M Instruct

D36

0.3B20.4 GB4 tok/s27465K ctx

embeddinggemma 300M

D35

granite embedding 107m multilingual

D33

0.11B20.3 GB2 tok/s27494K ctx

Falcon H1 Tiny 90M Instruct

D33

0.09B20.3 GB2 tok/s27495K ctx

👁 Alibaba
Qwen3-Coder 480B A35B Instruct

480B315.8 GB11 tok/s4K ctx

moe

👁 Alibaba
Qwen 3.5 397B A17B

397B265.1 GB21 tok/s4K ctx

moe

👁 Mistral
Mistral Large 3

675B437.2 GB5 tok/s4K ctx

+1moe

👁 Z.ai
GLM-5

744B493.0 GB4 tok/s4K ctx

moe

👁 Z.ai
GLM-5.1

754B499.1 GB4 tok/s4K ctx

moe

👁 Moonshot AI
Kimi K2.5

1000B637.5 GB3 tok/s4K ctx

moe

👁 Moonshot AI
Kimi K2.6

1000B637.5 GB3 tok/s4K ctx

+1moe

👁 DeepSeek
DeepSeek V3 671B

671B489.0 GB4 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V3.1 671B

671B489.0 GB4 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek V4 Pro

1600B884.0 GB3 tok/s4K ctx

moe

👁 DeepSeek
DeepSeek R1 671B

671B489.0 GB4 tok/s4K ctx

moe

👁 Meta
Llama 4 Maverick 17B 128E

400B267.0 GB21 tok/s4K ctx

moe

👁 Meta
Llama 3.1 405B

405B274.8 GB7 tok/s4K ctx

dense

👁 DeepSeek
DeepSeek V3.2

671B429.9 GB5 tok/s4K ctx

moe

👁 Unsloth
Qwen3.5 397B A17B

397B308.8 GB5 tok/s4K ctx

dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

NVIDIA GB200 192GB

192 GB VRAM

B100 192GB

192 GB VRAM

H100 NVL 188GB

188 GB VRAM

NVIDIA B200 180GB

180 GB VRAM