VOOZH about

URL: https://willitrunai.com/my-results/arc-b570-10gb

⇱ Intel Arc B570 10GB AI Tier List: 207 models ranked | WillItRunAI


AI Compatibility Tier List

Intel Arc B570 10GB

374 AI models ranked by how well they run on your 10 GB VRAM hardware. Best match: Qwen 3.5 4B (score: 94).

374

Models tested

207

Can run

10 GB

VRAM

56

Best tok/s

Tier Distribution

S 6
A 34
B 27
C 140
F 167
S: 6A: 34B: 27C: 140F: 167
S

S Tier -- Perfect Fit (6 models)

These models run flawlessly with headroom to spare.

👁 Alibaba
Qwen 3.5 4B
S94
4B6.5 GB56 tok/s41K ctx
dense
👁 Alibaba
Qwen 3.5 9B
S93
9B9.6 GB40 tok/s19K ctx
dense
👁 Alibaba
Qwen 3 8B
S92
8B9.0 GB45 tok/s23K ctx
dense
👁 Microsoft
Phi-4 Mini Reasoning 4B
S89
3.8B5.7 GB53 tok/s63K ctx
dense
👁 NVIDIA
Nemotron Nano 8B
S87
8B8.7 GB45 tok/s26K ctx
dense
👁 Alibaba
Qwen 3 4B
S86
4B6.5 GB56 tok/s33K ctx
dense
A

A Tier -- Great Fit (34 models)

Excellent performance with comfortable memory margins.

👁 Alibaba
Qwen 2.5 VL 7B
A85
7B7.0 GB52 tok/s33K ctx
dense
👁 Defog
SQLCoder 7B
A85
7B8.1 GB52 tok/s8K ctx
dense
👁 InternLM
InternVL2 8B
A84
8B8.7 GB45 tok/s8K ctx
dense
👁 Magistral AI
Magistral 7B
A83
7B8.1 GB52 tok/s8K ctx
dense
👁 Mistral
Ministral 3 8B
A82
8B9.0 GB45 tok/s23K ctx
multimodal
👁 OpenBMB
MiniCPM-V 2.6 8B
A82
8B8.7 GB45 tok/s2K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
A82
9B8.0 GB41 tok/s68K ctx
dense
👁 Jina AI
Jina Embeddings v3
A82
0.57B5.0 GB8 tok/s8K ctx
dense
👁 Google
Gemma 4 E4B
A81
8B8.1 GB34 tok/s40K ctx
dense
👁 Alibaba
Qwen 2.5 7B
A81
7B7.0 GB52 tok/s72K ctx
dense
👁 NVIDIA
Nemotron Nano 9B v2
A81
9B9.8 GB40 tok/s17K ctx
dense
👁 DevStral AI
DevStral 7B
A80
7B8.1 GB52 tok/s8K ctx
dense
👁 Mistral AI
Codestral Mamba 7B
A80
7B6.7 GB55 tok/s126K ctx
state-space
👁 BAAI
BGE M3
A79
0.57B4.2 GB8 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 3B
A78
3B5.9 GB42 tok/s46K ctx
dense
👁 IBM
Granite Code 8B
A77
8B8.7 GB45 tok/s8K ctx
dense
👁 IBM
Granite 4.1 8B
A76
8B9.2 GB45 tok/s21K ctx
dense
👁 Zhipu
GLM-4 9B
A76
9B8.0 GB41 tok/s68K ctx
dense
👁 WizardLM
WizardMath 7B
A76
7B8.1 GB52 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
A76
7B8.1 GB52 tok/s4K ctx
dense
👁 Mixedbread AI
mxbai Embed Large
A76
0.34B4.1 GB5 tok/s1K ctx
dense
👁 Google
Gemma 3 4B
A75
4B6.4 GB56 tok/s44K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 7B
A75
7B7.0 GB52 tok/s72K ctx
dense
👁 Google
Gemma 4 E2B
A75
5.1B5.5 GB54 tok/s128K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
A75
0.34B4.1 GB5 tok/s1K ctx
dense
👁 Microsoft
Phi 4 Mini 4B
A73
4B5.8 GB56 tok/s62K ctx
dense
👁 BAAI
BGE Large EN v1.5
A73
0.34B4.1 GB5 tok/s1K ctx
dense
A73
7B9.1 GB52 tok/s8K ctx
dense
👁 Meta
Llama 3.1 8B
A73
8B8.7 GB45 tok/s26K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 7B
A72
7B7.0 GB52 tok/s33K ctx
dense
👁 Mistral
Ministral 3 3B
A71
3B4.5 GB42 tok/s137K ctx
multimodal
7B8.1 GB52 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 3B
A71
3B5.9 GB42 tok/s46K ctx
dense
👁 Alibaba
Qwen 3.5 2B
A71
2B4.8 GB28 tok/s64K ctx
dense
B

B Tier -- Good Fit (27 models)

Solid performance, may need quantization or reduced context.

👁 TII
Falcon 7B Instruct
B70
7B6.3 GB53 tok/s8K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
B69
3.8B10.1 GB53 tok/s16K ctx
dense
👁 IBM
Granite Code 3B
B69
3B6.2 GB42 tok/s8K ctx
dense
👁 Nomic AI
Nomic Embed Text v1.5
B69
0.14B2.7 GB2 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 8B
B68
8B8.7 GB45 tok/s26K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
B68
4B10.2 GB56 tok/s15K ctx
dense
👁 Mistral
Mistral 7B Instruct v0.3
B67
7B8.1 GB52 tok/s8K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B67
1.7B4.6 GB24 tok/s33K ctx
dense
👁 IBM
Granite 4.1 3B
B67
3B5.0 GB42 tok/s82K ctx
dense
👁 01.AI
Yi Coder 9B
B63
9B8.9 GB41 tok/s29K ctx
dense
👁 Meta
Llama 3.2 3B
B63
3B5.4 GB42 tok/s59K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 1.5B
B63
1.5B3.2 GB21 tok/s33K ctx
dense
B62
0.02B2.2 GB2 tok/s0K ctx
dense
👁 Mistral AI
Pixtral 12B
B62
12B11.7 GB17 tok/s5K ctx
dense
👁 Mistral
Ministral 8B
B61
8B9.0 GB45 tok/s23K ctx
dense
B59
3B5.7 GB42 tok/s51K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
B59
7B7.0 GB52 tok/s4K ctx
dense
👁 OpenChat
OpenChat 7B
B57
7B8.1 GB52 tok/s8K ctx
dense
👁 IBM
Granite 3.1 8B
B57
8B8.7 GB52 tok/s26K ctx
state-space
👁 Teknium
OpenHermes 2.5 7B
B56
7B8.1 GB52 tok/s8K ctx
dense
👁 01.AI
Yi 1.5 9B
B56
9B8.9 GB41 tok/s4K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
B56
7B8.1 GB52 tok/s31K ctx
dense
👁 UC Berkeley
Starling LM 7B
B55
7B8.1 GB52 tok/s8K ctx
dense
Llama 2 7B Chat
B55
7B7.0 GB48 tok/s75K ctx
dense
falcon mamba 7b instruct Q4 K M
B55
7B7.0 GB55 tok/s75K ctx
dense
Mistral 7B Instruct v0.2
B55
7B7.0 GB48 tok/s75K ctx
dense
Mistral 7B Instruct v0.3
B55
7B7.0 GB48 tok/s75K ctx
dense
C

C Tier -- Tight Fit (140 models)

Runs with offloading or significant compromises.

Mamba Codestral 7B v0.1
C55
7B7.0 GB55 tok/s75K ctx
dense
Mistral 7B Instruct v0.3
C55
7B7.0 GB48 tok/s75K ctx
dense
Hermes 2 Pro Mistral 7B
C55
7B7.0 GB48 tok/s75K ctx
dense
zephyr 7B beta
C55
7B7.0 GB48 tok/s75K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C55
7B7.0 GB48 tok/s75K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
C55
1.5B3.2 GB21 tok/s33K ctx
dense
Meta Llama 3.1 8B Instruct
C55
8B7.7 GB42 tok/s55K ctx
dense
Falcon H1R 7B
C55
7B7.0 GB48 tok/s75K ctx
dense
llava llama 3 8b v1 1
C55
8B7.7 GB42 tok/s55K ctx
dense
zephyr 7B alpha
C55
7B7.0 GB48 tok/s75K ctx
dense
speechless zephyr code functionary 7b
C55
7B7.0 GB48 tok/s75K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
C55
8B7.7 GB42 tok/s55K ctx
dense
StarCoder2 7B
C55
7B7.0 GB48 tok/s75K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
C55
4B6.3 GB56 tok/s4K ctx
dense
japanese stablelm instruct gamma 7B
C55
7B7.0 GB48 tok/s75K ctx
dense
Meta Llama 3 8B Instruct
C55
8B7.7 GB42 tok/s55K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
C55
8B7.7 GB42 tok/s55K ctx
dense
Falcon H1 7B Instruct
C55
7B7.0 GB48 tok/s75K ctx
dense
Dolphin3.0 Llama3.1 8B
C55
8B7.7 GB42 tok/s55K ctx
dense
👁 Unsloth
Falcon H1R 7B
C55
7B7.0 GB48 tok/s75K ctx
dense
Llama 3 8B Instruct 32k v0.1
C55
8B7.7 GB42 tok/s55K ctx
dense
Meta Llama 3.1 8B Instruct
C55
8B7.7 GB42 tok/s55K ctx
dense
vntl llama3 8b v2
C55
8B7.7 GB42 tok/s55K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C54
8B7.7 GB42 tok/s55K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C54
8B7.7 GB42 tok/s55K ctx
dense
stabilityai japanese stablelm base gamma 7b
C54
7B7.0 GB48 tok/s75K ctx
dense
baichuan2 7b chat
C54
7B7.0 GB48 tok/s75K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C54
8B7.7 GB42 tok/s55K ctx
dense
DiscoPOP zephyr 7b gemma
C54
7B7.0 GB48 tok/s75K ctx
dense
Hermes 3 Llama 3.1 8B
C54
8B7.7 GB42 tok/s55K ctx
dense
starcoder2 7b
C54
7B7.0 GB48 tok/s75K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C54
7B7.0 GB48 tok/s75K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C54
7B7.0 GB48 tok/s75K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C54
7B7.0 GB48 tok/s75K ctx
dense
internlm2 math plus 7b IMat
C54
7B7.0 GB48 tok/s75K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C54
7B7.0 GB48 tok/s75K ctx
dense
internlm2 5 7b chat i1
C54
7B7.0 GB48 tok/s75K ctx
dense
👁 01.AI
Yi 1.5 6B
C54
6B6.5 GB61 tok/s4K ctx
dense
Hermes 2 Pro Llama 3 8B
C54
8B7.7 GB42 tok/s55K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C54
7B7.0 GB48 tok/s75K ctx
dense
Dolphin3.0 Llama3.1 8B
C54
8B7.7 GB42 tok/s55K ctx
dense
👁 Intel
Neural Chat 7B
C54
7B8.1 GB52 tok/s8K ctx
dense
MD Judge v0 2 internlm2 7b i1
C54
7B7.0 GB48 tok/s75K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C54
7B7.0 GB48 tok/s75K ctx
dense
granite 8b code instruct 4k
C54
8B7.7 GB42 tok/s55K ctx
dense
jointpreferences mistral 7b sft helpful
C54
7B7.0 GB48 tok/s75K ctx
dense
zephyr 7b dpo full i1
C54
7B7.0 GB48 tok/s75K ctx
dense
blossom v3 baichuan2 7b i1
C54
7B7.0 GB48 tok/s75K ctx
dense
dolphin 2.9.4 llama3.1 8b
C54
8B7.7 GB42 tok/s55K ctx
dense
EXAONE 3.5 7.8B Instruct
C54
7.8B7.6 GB43 tok/s58K ctx
dense
blossom v1 baichuan 7b i1
C54
7B7.0 GB48 tok/s75K ctx
dense
EXAONE 3.5 7.8B Instruct
C54
7.8B7.6 GB43 tok/s58K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C54
7.8B7.6 GB43 tok/s58K ctx
dense
openchat 3.6 8b 20240522 IMat
C54
8B7.7 GB42 tok/s55K ctx
dense
aya expanse 8b
C54
8B7.7 GB42 tok/s55K ctx
dense
exaone 3.0 7.8b it
C54
7.8B7.6 GB43 tok/s58K ctx
dense
dolphin v2 8b abliterated i1
C54
8B7.7 GB42 tok/s55K ctx
dense
aya expanse 8b orthogonal heretic i1
C54
8B7.7 GB42 tok/s55K ctx
dense
👁 TinyLlama
TinyLlama 1.1B
C54
1.1B2.9 GB15 tok/s4K ctx
dense
aya expanse 8b orthogonal heretic
C54
8B7.7 GB42 tok/s55K ctx
dense
Yi 1.5 6B Chat
C54
6B6.3 GB56 tok/s101K ctx
dense
internlm2 5 1 8b chat i1
C54
8B7.7 GB42 tok/s55K ctx
dense
internlm3 8b instruct abliterated i1
C54
8B7.7 GB42 tok/s55K ctx
dense
stablelm 2 zephyr 1 6b
C54
6B6.3 GB56 tok/s101K ctx
dense
👁 Meta
Llama 3.2 11B Vision
C54
11B10.6 GB23 tok/s11K ctx
vision
👁 BigCode
StarCoder2 7B
C54
7B6.7 GB53 tok/s16K ctx
dense
Yi 1.5 6B Chat
C54
6B6.3 GB56 tok/s101K ctx
dense
stablelm 2 1 6b chat imatrix
C54
6B6.3 GB56 tok/s101K ctx
dense
HelpingAI2 6B
C53
6B6.3 GB56 tok/s101K ctx
dense
HelpingAI2 6B i1
C53
6B6.3 GB56 tok/s101K ctx
dense
👁 Cohere
Aya Expanse 8B
C53
8B8.7 GB45 tok/s8K ctx
dense
👁 Google
Gemma 2 2B
C53
2B4.7 GB28 tok/s8K ctx
dense
8B8.7 GB45 tok/s26K ctx
dense
HelpingAI2.5 5B i1
C52
5B5.5 GB67 tok/s138K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
C52
1.5B3.2 GB21 tok/s131K ctx
dense
👁 Unsloth
Qwen3.5 9B
C51
9B8.4 GB37 tok/s40K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C51
9B8.4 GB37 tok/s40K ctx
dense
Qwen3.5 9B
C51
9B8.4 GB37 tok/s40K ctx
dense
Yi Coder 9B Chat
C51
9B8.4 GB37 tok/s40K ctx
dense
glm 4 9b chat 1m
C51
9B8.4 GB37 tok/s40K ctx
dense
👁 Unsloth
Qwen3.5 4B
C51
4B4.8 GB56 tok/s193K ctx
dense
Yi 1.5 9B Chat
C51
9B8.4 GB37 tok/s40K ctx
dense
gemma 3 4b it
C51
4B4.8 GB56 tok/s193K ctx
dense
👁 Mistral
Mistral Nemo 12B
C51
12B11.7 GB17 tok/s5K ctx
dense
gemma 3 4b it
C51
4B4.8 GB56 tok/s193K ctx
dense
Yi 9B Coder i1
C51
9B8.4 GB37 tok/s40K ctx
dense
HelpingAI2 9B
C51
9B8.4 GB37 tok/s40K ctx
dense
HelpingAI2 9B i1
C50
9B8.4 GB37 tok/s40K ctx
dense
HelpingAI 9B 200k i1
C50
9B8.4 GB37 tok/s40K ctx
dense
HelpingAI 9B i1
C50
9B8.4 GB37 tok/s40K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C50
10.7B9.7 GB31 tok/s20K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C50
10.7B9.7 GB31 tok/s20K ctx
dense
HelpingAI2.5 10B i1
C50
10B9.2 GB34 tok/s27K ctx
dense
solar finalised finetuned Model 10.7B i1
C50
10.7B9.7 GB31 tok/s20K ctx
dense
👁 Google
Gemma 3 1B
C50
1B2.9 GB14 tok/s33K ctx
dense
Helply 10.2b chat i1
C50
10.2B9.3 GB33 tok/s25K ctx
dense
SOLAR 10.7B v1.0
C50
10.7B9.7 GB31 tok/s20K ctx
dense
Llama 3.2 3B Instruct
C49
3B4.4 GB42 tok/s270K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C48
3B4.1 GB42 tok/s285K ctx
dense
Llama 3.2 3B Instruct
C48
3B4.1 GB42 tok/s285K ctx
dense
Ministral 3 3B Instruct 2512
C48
3B4.1 GB42 tok/s285K ctx
dense
HELVETE 3B
C48
3B4.1 GB42 tok/s285K ctx
dense
Hermes 3 Llama 3.2 3B
C48
3B4.1 GB42 tok/s285K ctx
dense
stablelm zephyr 3b
C48
3B4.1 GB42 tok/s285K ctx
dense
StarCoder2 3B
C48
3B4.1 GB42 tok/s285K ctx
dense
AI21 Jamba Reasoning 3B
C48
3B4.1 GB42 tok/s285K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C48
0.5B2.4 GB7 tok/s131K ctx
dense
stablelm 3b 4e1t
C48
3B4.1 GB42 tok/s285K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C48
3B4.1 GB42 tok/s285K ctx
dense
ai21labs AI21 Jamba2 3B
C48
3B4.1 GB42 tok/s285K ctx
dense
HelpingAI 3B hindi i1
C48
3B4.1 GB42 tok/s285K ctx
dense
AI21 Jamba2 3B
C48
3B4.1 GB42 tok/s285K ctx
dense
HelpingAI 3B hindi
C48
3B4.1 GB42 tok/s285K ctx
dense
AI21 Jamba2 3B i1
C48
3B4.1 GB42 tok/s285K ctx
dense
👁 Alibaba
Qwen 3 0.6B
C47
0.6B3.1 GB8 tok/s33K ctx
dense
👁 Meta
Llama 3.2 1B
C47
1B3.0 GB14 tok/s128K ctx
dense
👁 BigCode
StarCoder2 3B
C47
3B4.2 GB42 tok/s16K ctx
dense
gemma 2 2b it
C47
2B3.8 GB28 tok/s441K ctx
dense
EXAONE 3.5 2.4B Instruct
C46
2.4B3.6 GB34 tok/s378K ctx
dense
👁 Google
gemma 2b
C46
2B3.4 GB28 tok/s470K ctx
dense
Gemmasutra Mini 2B v1
C46
2B3.4 GB28 tok/s470K ctx
dense
gemma 2 2b it
C45
2B3.4 GB28 tok/s470K ctx
dense
👁 Alibaba
Qwen 3.5 0.6B
C45
0.6B3.1 GB8 tok/s131K ctx
dense
👁 Qwen
Qwen2.5 1.5B Instruct
C44
1.5B3.0 GB21 tok/s654K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B
C44
1.5B3.0 GB21 tok/s654K ctx
dense
Yi Coder 1.5B Chat
C44
1.5B3.0 GB21 tok/s654K ctx
dense
stablelm 2 zephyr 1.6b
C44
1.6B3.1 GB22 tok/s608K ctx
dense
logos16v2 stablelm2 1.6b i1
C44
1.6B3.1 GB22 tok/s608K ctx
dense
Yi Coder 1.5B
C43
1.5B3.0 GB21 tok/s654K ctx
dense
👁 Unsloth
Falcon H1 1.5B Instruct
C43
1.5B3.0 GB21 tok/s654K ctx
dense
EXAONE 4.0 1.2B
C42
1.2B2.8 GB17 tok/s838K ctx
dense
TinyLlama 1.1B Chat v1.0
C42
1.1B2.7 GB15 tok/s922K ctx
dense
Llama 3.2 1B Instruct Q8 0
C42
1B2.8 GB14 tok/s994K ctx
dense
TinyLlama 1.1B Chat v0.3
C42
1.1B2.7 GB15 tok/s922K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
C42
1.1B2.7 GB15 tok/s922K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
C42
0.5B2.4 GB7 tok/s131K ctx
dense
Llama 3.2 1B Instruct
C42
1B2.6 GB14 tok/s1023K ctx
dense
gemma 3 1b it
C42
1B2.6 GB14 tok/s1023K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
C41
1.1B2.7 GB15 tok/s922K ctx
dense
Falcon3 1B Instruct abliterated
C41
1B2.6 GB14 tok/s1023K ctx
dense
F

F Tier -- Can't Run (167 models)

Too heavy for this hardware.

SmolVLM 500M Instruct
D39
0.5B2.4 GB7 tok/s1230K ctx
dense
gemma 3 12b it
D39
12B10.6 GB19 tok/s9K ctx
dense
embeddinggemma 300M
D37
0.3B2.2 GB4 tok/s1257K ctx
dense
granite embedding 107m multilingual
D35
0.11B2.1 GB2 tok/s1286K ctx
dense
Falcon H1 Tiny 90M Instruct
D35
0.09B2.1 GB2 tok/s1287K ctx
dense
👁 Meta
Llama 3.1 70B
F0
70B49.5 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.3 70B
F0
70B49.5 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 14B
F0
14B13.4 GB11 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 32B
F0
32B25.3 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 72B
F0
72B50.7 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 14B
F0
14B13.4 GB11 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 32B
F0
32B25.3 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 14B
F0
14B12.9 GB12 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 32B
F0
32B25.3 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
F0
235B148.1 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3 30B A3B
F0
30.5B22.0 GB5 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 30B A3B Instruct
F0
30.5B22.0 GB5 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder-Next
F0
80B52.2 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B297.6 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-VL 30B A3B Instruct
F0
30B21.7 GB5 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 27B
F0
27B21.5 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3.5 35B A3B
F0
35B24.7 GB4 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.6 35B A3B
F0
35B27.4 GB4 tok/s4K ctx
+1moe
👁 Alibaba
Qwen 3.6 27B
F0
27B19.3 GB2 tok/s4K ctx
+1dense
👁 Alibaba
Qwen 3.5 122B A10B
F0
122B78.8 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B246.9 GB2 tok/s4K ctx
moe
👁 Google
Gemma 2 9B
F0
9B12.5 GB14 tok/s8K ctx
dense
👁 Google
Gemma 2 27B
F0
27B29.6 GB2 tok/s4K ctx
dense
👁 Google
Gemma 3 12B
F0
12B14.1 GB9 tok/s4K ctx
dense
👁 Google
Gemma 3 27B
F0
27B29.6 GB2 tok/s4K ctx
dense
👁 Mistral
Ministral 3 14B
F0
14B12.9 GB12 tok/s4K ctx
multimodal
👁 Mistral
Mistral Small 24B
F0
24B19.0 GB3 tok/s4K ctx
dense
👁 Mistral
Mistral Small 3.2 24B
F0
24B19.0 GB3 tok/s4K ctx
vision
👁 Mistral
Mixtral 8x7B
F0
47B32.5 GB2 tok/s4K ctx
moe
👁 Mistral
Mixtral 8x22B
F0
141B91.3 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 Distill 14B
F0
14B13.4 GB11 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 32B
F0
32B25.3 GB2 tok/s4K ctx
dense
F0
14B13.5 GB11 tok/s4K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
F0
14.7B13.9 GB10 tok/s4K ctx
dense
👁 IBM
Granite 4.1 30B
F0
30B24.1 GB2 tok/s4K ctx
dense
👁 AllenAI
OLMo 2 13B
F0
13B12.3 GB14 tok/s4K ctx
dense
👁 Cohere
Command R 35B
F0
35B25.7 GB2 tok/s4K ctx
dense
👁 TII
Falcon 40B Instruct
F0
40B32.5 GB2 tok/s4K ctx
dense
👁 WizardLM
WizardLM 13B
F0
13B22.0 GB4 tok/s4K ctx
dense
👁 BigCode
StarCoder 7B
F0
7B13.5 GB20 tok/s8K ctx
dense
👁 BigCode
StarCoder 15B
F0
15B27.3 GB3 tok/s4K ctx
dense
👁 Meta
CodeLlama 7B Instruct
F0
7B14.0 GB19 tok/s8K ctx
dense
👁 Meta
CodeLlama 13B Instruct
F0
13B22.0 GB4 tok/s4K ctx
dense
👁 BigCode
StarCoder2 15B
F0
15B13.9 GB8 tok/s4K ctx
dense
👁 MosaicML
MPT-7B-Instruct
F0
7B14.0 GB19 tok/s8K ctx
dense
👁 MosaicML
MPT-30B-Instruct
F0
30B46.9 GB2 tok/s4K ctx
dense
👁 InternLM
InternLM 7B
F0
7B14.0 GB19 tok/s8K ctx
dense
👁 InternLM
InternLM Chat 7B
F0
7B14.0 GB19 tok/s8K ctx
dense
👁 Mistral
Devstral Small 1.1
F0
24B19.0 GB3 tok/s4K ctx
dense
👁 Mistral
Devstral Small 2 24B Instruct
F0
24B19.0 GB3 tok/s4K ctx
dense
👁 Mistral
Devstral 2 123B Instruct
F0
123B82.3 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 4 119B
F0
119B79.9 GB2 tok/s4K ctx
moe
👁 Mistral
Leanstral 119B A6B
F0
119B83.3 GB2 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B419.0 GB2 tok/s4K ctx
+1moe
👁 Mistral
Magistral Small 2507
F0
24B19.0 GB3 tok/s4K ctx
dense
👁 Mistral
Codestral 2 25.08
F0
22B17.8 GB4 tok/s4K ctx
dense
F0
744B474.8 GB2 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B480.9 GB2 tok/s4K ctx
moe
F0
1000B619.3 GB2 tok/s4K ctx
moe
F0
1000B619.3 GB2 tok/s4K ctx
+1moe
👁 Moonshot AI
Kimi Linear 48B A3B
F0
48B32.1 GB2 tok/s4K ctx
linear
👁 Nous Research
Nous Hermes 1.0
F0
9B19.6 GB7 tok/s4K ctx
dense
👁 Nous Research
Nous Dolphin 13B
F0
13B23.5 GB3 tok/s4K ctx
dense
👁 Baichuan
Baichuan 7B
F0
7B14.0 GB19 tok/s8K ctx
dense
👁 Baichuan
Baichuan 13B
F0
13B23.5 GB3 tok/s4K ctx
dense
👁 Cerebras
Cerebras-GPT 13B
F0
13B21.0 GB4 tok/s4K ctx
dense
👁 Stability AI
StableLM 2 12B
F0
12B22.7 GB3 tok/s4K ctx
dense
👁 InternLM
InternLM 20B
F0
20B34.6 GB2 tok/s4K ctx
dense
👁 01.AI
Yi 34B Chat
F0
34B26.3 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3 671B
F0
671B470.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B470.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B865.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Flash
F0
284B161.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B470.8 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 16B
F0
16B15.0 GB17 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B204.5 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B204.5 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek LLM 7B
F0
7B13.5 GB20 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek LLM 67B
F0
67B48.6 GB2 tok/s4K ctx
dense
👁 Meta
Llama 4 Scout 17B 16E
F0
109B71.3 GB2 tok/s4K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B248.8 GB2 tok/s4K ctx
moe
👁 Cohere
Command R+ 104B
F0
104B68.8 GB2 tok/s4K ctx
dense
👁 Cohere
Command A 111B
F0
111B73.5 GB2 tok/s4K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
F0
14B13.5 GB11 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 34B
F0
34B26.3 GB2 tok/s4K ctx
dense
👁 Mistral AI
Codestral 22B
F0
22B17.8 GB4 tok/s4K ctx
dense
👁 Mistral AI
Pixtral Large 124B
F0
124B82.9 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 VL 72B
F0
72B50.7 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
F0
72B50.7 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 70B
F0
70B49.5 GB2 tok/s4K ctx
dense
👁 LLaVA
LLaVA 1.5 7B
F0
7B14.0 GB19 tok/s4K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
F0
13B22.0 GB4 tok/s4K ctx
dense
F0
19B15.9 GB6 tok/s4K ctx
dense
👁 LMSYS
Vicuna 7B
F0
7B14.0 GB19 tok/s4K ctx
dense
👁 LMSYS
Vicuna 13B
F0
13B22.0 GB4 tok/s4K ctx
dense
👁 IBM
Granite Code 20B
F0
20B17.3 GB5 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 20B
F0
21B17.2 GB10 tok/s4K ctx
moe
👁 Allen AI
OLMo 2 32B
F0
32B25.3 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 3 Nano 30B
F0
30B22.6 GB2 tok/s4K ctx
dense
👁 LG AI
EXAONE 4.0 32B
F0
32B25.3 GB2 tok/s4K ctx
dense
F0
24B19.0 GB3 tok/s4K ctx
dense
👁 Meta
Llama 3.1 405B
F0
405B256.6 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
F0
70B49.5 GB2 tok/s4K ctx
dense
👁 IBM
Granite Code 34B
F0
34B26.3 GB2 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 120B
F0
117B78.2 GB2 tok/s4K ctx
dense
👁 Cohere
Aya Expanse 32B
F0
32B23.9 GB2 tok/s4K ctx
dense
👁 Mistral AI
Mistral Small 3.1 24B
F0
24B19.0 GB3 tok/s4K ctx
dense
👁 Google
Gemma 4 26B A4B
F0
25.2B20.9 GB6 tok/s4K ctx
moe
👁 Google
Gemma 4 31B
F0
30.7B35.3 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B411.7 GB2 tok/s4K ctx
moe
👁 NVIDIA
Nemotron Cascade 2 30B A3B
F0
30B23.1 GB5 tok/s4K ctx
moe
MiniMax M2.7
F0
230B146.0 GB2 tok/s4K ctx
moe
Solar Open 100B
F0
100B74.6 GB2 tok/s4K ctx
dense
Baichuan M2 32B Q4 K M
F0
32B25.2 GB2 tok/s4K ctx
dense
baichuan inc Baichuan M2 32B
F0
32B25.2 GB2 tok/s4K ctx
dense
Codestral 22B v0.1
F0
22B17.9 GB4 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B19.4 GB3 tok/s4K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
F0
24B19.4 GB3 tok/s4K ctx
dense
internlm JanusCoder 14B
F0
14B12.1 GB13 tok/s4K ctx
dense
internlm2 5 20b chat
F0
20B16.4 GB5 tok/s4K ctx
dense
NousResearch Hermes 4 14B
F0
14B12.1 GB13 tok/s4K ctx
dense
starcoder2 15b instruct v0.1
F0
15B12.8 GB10 tok/s4K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
F0
48B36.8 GB2 tok/s4K ctx
dense
internlm2 limarp chat 20b
F0
20B16.4 GB5 tok/s4K ctx
dense
Phi 4 reasoning vision 15B
F0
15B12.8 GB10 tok/s4K ctx
dense
Codestral 22B v0.1 IMat
F0
22B17.9 GB4 tok/s4K ctx
dense
EXAONE 4.0 32B
F0
32B25.2 GB2 tok/s4K ctx
dense
K EXAONE 236B A23B
F0
236B173.5 GB2 tok/s4K ctx
dense
Codestral 22B v0.1
F0
22B17.9 GB4 tok/s4K ctx
dense
Qwen3.5 35B A3B
F0
35B27.4 GB2 tok/s4K ctx
dense
starcoder2 15b instruct v0.1
F0
15B12.8 GB10 tok/s4K ctx
dense
gemma 3 27b it
F0
27B21.5 GB2 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F0
70B52.8 GB2 tok/s4K ctx
dense
Mistral Small 24B Instruct 2501
F0
24B19.4 GB3 tok/s4K ctx
dense
mistral small 3.1 24b instruct 2503 hf
F0
24B19.4 GB3 tok/s4K ctx
dense
aya expanse 32b heretic MPOA i1
F0
32B25.2 GB2 tok/s4K ctx
dense
Baichuan M3 235B
F0
235B172.8 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0
235B172.8 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F0
72B54.3 GB2 tok/s4K ctx
dense
Codestral 21B Pruned i1
F0
21B17.2 GB4 tok/s4K ctx
dense
Codestral 22B v0.1 i1
F0
22B17.9 GB4 tok/s4K ctx
dense
Codestral RAG 19B Pruned i1
F0
19B15.7 GB5 tok/s4K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
F0
24B19.4 GB3 tok/s4K ctx
dense
HelpingAI 15B i1
F0
15B12.8 GB10 tok/s4K ctx
dense
internlm2 math plus 20b i1
F0
20B16.4 GB5 tok/s4K ctx
dense
Solar Open 100B i1
F0
100B74.6 GB2 tok/s4K ctx
dense
Solar Open 69B REAP i1
F0
69B52.1 GB2 tok/s4K ctx
dense
starcoder2 15b i1
F0
15B12.8 GB10 tok/s4K ctx
dense
Hermes 4.3 36B
F0
36B28.1 GB2 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F0
70B52.8 GB2 tok/s4K ctx
dense
Codestral 22B v0.1
F0
22B17.9 GB4 tok/s4K ctx
dense
StarCoder2 15B
F0
15B12.8 GB10 tok/s4K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
F0
14B12.1 GB13 tok/s4K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
F0
14B12.1 GB13 tok/s4K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
F0
14B12.1 GB13 tok/s4K ctx
dense
👁 Unsloth
gemma 3 27b it
F0
27B21.5 GB2 tok/s4K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
F0
24B19.4 GB3 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
F0
122B76.0 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 27B
F0
27B21.5 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
F0
35B27.4 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 397B A17B
F0
397B290.6 GB2 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B19.4 GB3 tok/s4K ctx
dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

RTX 3080 10GB

10 GB VRAM

View tier list

GTX 1080 Ti 11GB

11 GB VRAM

View tier list

RTX 2080 Ti 11GB

11 GB VRAM

View tier list

RTX 3050 8GB

8 GB VRAM

View tier list
Full Intel Arc B570 10GB pageCompare this hardware