VOOZH about

URL: https://willitrunai.com/my-results/rx-7700s-8gb

⇱ Radeon RX 7700S 8GB AI Tier List: 195 models ranked | WillItRunAI


AI Compatibility Tier List

Radeon RX 7700S 8GB

374 AI models ranked by how well they run on your 8 GB VRAM hardware. Best match: Qwen 3.5 4B (score: 95).

374

Models tested

195

Can run

8 GB

VRAM

56

Best tok/s

Tier Distribution

S 3
A 31
B 20
C 141
F 179
S: 3A: 31B: 20C: 141F: 179
S

S Tier -- Perfect Fit (3 models)

These models run flawlessly with headroom to spare.

👁 Alibaba
Qwen 3.5 4B
S95
4B6.3 GB56 tok/s28K ctx
dense
👁 Microsoft
Phi-4 Mini Reasoning 4B
S92
3.8B5.5 GB53 tok/s43K ctx
dense
👁 Alibaba
Qwen 3 4B
S87
4B6.3 GB56 tok/s28K ctx
dense
A

A Tier -- Great Fit (31 models)

Excellent performance with comfortable memory margins.

👁 Jina AI
Jina Embeddings v3
A84
0.57B4.8 GB8 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 VL 7B
A81
7B6.8 GB43 tok/s33K ctx
dense
👁 Defog
SQLCoder 7B
A81
7B7.9 GB43 tok/s8K ctx
dense
👁 BAAI
BGE M3
A81
0.57B4.0 GB8 tok/s8K ctx
dense
👁 Alibaba
Qwen 3.5 9B
A80
9B9.4 GB18 tok/s6K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 3B
A80
3B5.7 GB42 tok/s33K ctx
dense
👁 Mistral AI
Codestral Mamba 7B
A80
7B6.5 GB46 tok/s67K ctx
state-space
👁 Alibaba
Qwen 3 8B
A79
8B8.8 GB23 tok/s10K ctx
dense
👁 Magistral AI
Magistral 7B
A79
7B7.9 GB43 tok/s8K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
A78
9B7.8 GB34 tok/s21K ctx
dense
👁 Google
Gemma 4 E4B
A77
8B7.9 GB28 tok/s18K ctx
dense
👁 Alibaba
Qwen 2.5 7B
A77
7B6.8 GB43 tok/s38K ctx
dense
👁 Mixedbread AI
mxbai Embed Large
A77
0.34B3.9 GB5 tok/s1K ctx
dense
👁 Google
Gemma 4 E2B
A77
5.1B5.3 GB45 tok/s96K ctx
dense
👁 DevStral AI
DevStral 7B
A77
7B7.9 GB43 tok/s8K ctx
dense
👁 Google
Gemma 3 4B
A77
4B6.2 GB55 tok/s30K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
A76
0.34B3.9 GB5 tok/s1K ctx
dense
👁 Microsoft
Phi 4 Mini 4B
A76
4B5.6 GB56 tok/s42K ctx
dense
👁 NVIDIA
Nemotron Nano 8B
A75
8B8.5 GB25 tok/s12K ctx
dense
👁 BAAI
BGE Large EN v1.5
A75
0.34B3.9 GB5 tok/s1K ctx
dense
👁 Mistral
Ministral 3 3B
A73
3B4.3 GB42 tok/s98K ctx
multimodal
👁 Alibaba
Qwen 2.5 3B
A73
3B5.7 GB42 tok/s33K ctx
dense
👁 Alibaba
Qwen 3.5 2B
A73
2B4.6 GB28 tok/s48K ctx
dense
👁 Zhipu
GLM-4 9B
A72
9B7.8 GB34 tok/s21K ctx
dense
👁 WizardLM
WizardMath 7B
A72
7B7.9 GB43 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
A72
7B7.9 GB43 tok/s4K ctx
dense
👁 InternLM
InternVL2 8B
A72
8B8.5 GB25 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 7B
A71
7B6.8 GB43 tok/s38K ctx
dense
👁 TII
Falcon 7B Instruct
A71
7B6.1 GB44 tok/s8K ctx
dense
👁 IBM
Granite Code 3B
A70
3B6.0 GB42 tok/s8K ctx
dense
👁 OpenBMB
MiniCPM-V 2.6 8B
A70
8B8.5 GB25 tok/s2K ctx
dense
B

B Tier -- Good Fit (20 models)

Solid performance, may need quantization or reduced context.

👁 Mistral
Ministral 3 8B
B70
8B8.8 GB23 tok/s10K ctx
multimodal
👁 Nomic AI
Nomic Embed Text v1.5
B70
0.14B2.5 GB2 tok/s8K ctx
dense
👁 IBM
Granite 4.1 3B
B69
3B4.8 GB42 tok/s59K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B69
1.7B4.4 GB24 tok/s33K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 7B
B68
7B6.8 GB43 tok/s33K ctx
dense
7B7.9 GB43 tok/s4K ctx
dense
👁 Meta
Llama 3.2 3B
B66
3B5.2 GB42 tok/s42K ctx
dense
👁 IBM
Granite Code 8B
B65
8B8.5 GB25 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 1.5B
B64
1.5B3.0 GB21 tok/s33K ctx
dense
👁 Mistral
Mistral 7B Instruct v0.3
B64
7B7.9 GB43 tok/s8K ctx
dense
👁 IBM
Granite 4.1 8B
B63
8B9.0 GB22 tok/s9K ctx
dense
B63
0.02B2.0 GB2 tok/s0K ctx
dense
B62
3B5.5 GB42 tok/s37K ctx
dense
👁 Meta
Llama 3.1 8B
B61
8B8.5 GB25 tok/s12K ctx
dense
B60
7B8.9 GB26 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 8B
B56
8B8.5 GB25 tok/s12K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
B56
4B6.1 GB56 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
B56
1.5B3.0 GB21 tok/s33K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
B56
7B6.8 GB43 tok/s4K ctx
dense
👁 TinyLlama
TinyLlama 1.1B
B55
1.1B2.7 GB15 tok/s4K ctx
dense
C

C Tier -- Tight Fit (141 models)

Runs with offloading or significant compromises.

👁 Google
Gemma 2 2B
C55
2B4.5 GB28 tok/s8K ctx
dense
👁 01.AI
Yi 1.5 6B
C55
6B6.3 GB51 tok/s4K ctx
dense
Yi 1.5 6B Chat
C55
6B6.1 GB46 tok/s60K ctx
dense
stablelm 2 zephyr 1 6b
C55
6B6.1 GB46 tok/s60K ctx
dense
Yi 1.5 6B Chat
C54
6B6.1 GB46 tok/s60K ctx
dense
stablelm 2 1 6b chat imatrix
C54
6B6.1 GB46 tok/s60K ctx
dense
HelpingAI2 6B
C54
6B6.1 GB46 tok/s60K ctx
dense
HelpingAI2 6B i1
C54
6B6.1 GB46 tok/s60K ctx
dense
HelpingAI2.5 5B i1
C54
5B5.3 GB56 tok/s89K ctx
dense
👁 BigCode
StarCoder2 7B
C54
7B6.5 GB43 tok/s16K ctx
dense
👁 OpenChat
OpenChat 7B
C53
7B7.9 GB43 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
C53
1.5B3.0 GB21 tok/s131K ctx
dense
👁 Unsloth
Qwen3.5 4B
C53
4B4.6 GB56 tok/s132K ctx
dense
gemma 3 4b it
C53
4B4.6 GB56 tok/s132K ctx
dense
gemma 3 4b it
C53
4B4.6 GB56 tok/s132K ctx
dense
👁 Teknium
OpenHermes 2.5 7B
C52
7B7.9 GB43 tok/s8K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
C52
7B7.9 GB43 tok/s17K ctx
dense
👁 UC Berkeley
Starling LM 7B
C52
7B7.9 GB43 tok/s8K ctx
dense
Llama 2 7B Chat
C51
7B6.8 GB40 tok/s40K ctx
dense
falcon mamba 7b instruct Q4 K M
C51
7B6.8 GB46 tok/s40K ctx
dense
Mistral 7B Instruct v0.2
C51
7B6.8 GB40 tok/s40K ctx
dense
Mistral 7B Instruct v0.3
C51
7B6.8 GB40 tok/s40K ctx
dense
👁 01.AI
Yi Coder 9B
C51
9B8.7 GB21 tok/s9K ctx
dense
Mamba Codestral 7B v0.1
C51
7B6.8 GB46 tok/s40K ctx
dense
Mistral 7B Instruct v0.3
C51
7B6.8 GB40 tok/s40K ctx
dense
Hermes 2 Pro Mistral 7B
C51
7B6.8 GB40 tok/s40K ctx
dense
zephyr 7B beta
C51
7B6.8 GB40 tok/s40K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C51
7B6.8 GB40 tok/s40K ctx
dense
Meta Llama 3.1 8B Instruct
C51
8B7.5 GB35 tok/s24K ctx
dense
👁 Google
Gemma 3 1B
C51
1B2.7 GB14 tok/s33K ctx
dense
Falcon H1R 7B
C51
7B6.8 GB40 tok/s40K ctx
dense
llava llama 3 8b v1 1
C51
8B7.5 GB35 tok/s24K ctx
dense
zephyr 7B alpha
C51
7B6.8 GB40 tok/s40K ctx
dense
speechless zephyr code functionary 7b
C51
7B6.8 GB40 tok/s40K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
C51
8B7.5 GB35 tok/s24K ctx
dense
StarCoder2 7B
C51
7B6.8 GB40 tok/s40K ctx
dense
Meta Llama 3 8B Instruct
C51
8B7.5 GB35 tok/s24K ctx
dense
japanese stablelm instruct gamma 7B
C51
7B6.8 GB40 tok/s40K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
C51
8B7.5 GB35 tok/s24K ctx
dense
Llama 3.2 3B Instruct
C51
3B4.2 GB42 tok/s188K ctx
dense
Dolphin3.0 Llama3.1 8B
C51
8B7.5 GB35 tok/s24K ctx
dense
Falcon H1 7B Instruct
C51
7B6.8 GB40 tok/s40K ctx
dense
Llama 3 8B Instruct 32k v0.1
C51
8B7.5 GB35 tok/s24K ctx
dense
👁 Unsloth
Falcon H1R 7B
C51
7B6.8 GB40 tok/s40K ctx
dense
Meta Llama 3.1 8B Instruct
C51
8B7.5 GB35 tok/s24K ctx
dense
vntl llama3 8b v2
C51
8B7.5 GB35 tok/s24K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C51
8B7.5 GB35 tok/s24K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C51
8B7.5 GB35 tok/s24K ctx
dense
stabilityai japanese stablelm base gamma 7b
C51
7B6.8 GB40 tok/s40K ctx
dense
baichuan2 7b chat
C51
7B6.8 GB40 tok/s40K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C51
8B7.5 GB35 tok/s24K ctx
dense
DiscoPOP zephyr 7b gemma
C51
7B6.8 GB40 tok/s40K ctx
dense
Hermes 3 Llama 3.1 8B
C51
8B7.5 GB35 tok/s24K ctx
dense
starcoder2 7b
C51
7B6.8 GB40 tok/s40K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C51
7B6.8 GB40 tok/s40K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C51
7B6.8 GB40 tok/s40K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C51
7B6.8 GB40 tok/s40K ctx
dense
internlm2 math plus 7b IMat
C51
7B6.8 GB40 tok/s40K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C51
7B6.8 GB40 tok/s40K ctx
dense
Hermes 2 Pro Llama 3 8B
C51
8B7.5 GB35 tok/s24K ctx
dense
internlm2 5 7b chat i1
C51
7B6.8 GB40 tok/s40K ctx
dense
Dolphin3.0 Llama3.1 8B
C51
8B7.5 GB35 tok/s24K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C51
7B6.8 GB40 tok/s40K ctx
dense
👁 Intel
Neural Chat 7B
C51
7B7.9 GB43 tok/s8K ctx
dense
MD Judge v0 2 internlm2 7b i1
C51
7B6.8 GB40 tok/s40K ctx
dense
granite 8b code instruct 4k
C51
8B7.5 GB35 tok/s24K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C51
7B6.8 GB40 tok/s40K ctx
dense
jointpreferences mistral 7b sft helpful
C51
7B6.8 GB40 tok/s40K ctx
dense
zephyr 7b dpo full i1
C51
7B6.8 GB40 tok/s40K ctx
dense
dolphin 2.9.4 llama3.1 8b
C51
8B7.5 GB35 tok/s24K ctx
dense
blossom v3 baichuan2 7b i1
C51
7B6.8 GB40 tok/s40K ctx
dense
EXAONE 3.5 7.8B Instruct
C51
7.8B7.4 GB36 tok/s27K ctx
dense
blossom v1 baichuan 7b i1
C51
7B6.8 GB40 tok/s40K ctx
dense
EXAONE 3.5 7.8B Instruct
C51
7.8B7.4 GB36 tok/s27K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C51
7.8B7.4 GB36 tok/s27K ctx
dense
openchat 3.6 8b 20240522 IMat
C51
8B7.5 GB35 tok/s24K ctx
dense
aya expanse 8b
C51
8B7.5 GB35 tok/s24K ctx
dense
exaone 3.0 7.8b it
C51
7.8B7.4 GB36 tok/s27K ctx
dense
dolphin v2 8b abliterated i1
C50
8B7.5 GB35 tok/s24K ctx
dense
aya expanse 8b orthogonal heretic i1
C50
8B7.5 GB35 tok/s24K ctx
dense
aya expanse 8b orthogonal heretic
C50
8B7.5 GB35 tok/s24K ctx
dense
internlm2 5 1 8b chat i1
C50
8B7.5 GB35 tok/s24K ctx
dense
internlm3 8b instruct abliterated i1
C50
8B7.5 GB35 tok/s24K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C50
3B3.9 GB42 tok/s203K ctx
dense
Llama 3.2 3B Instruct
C50
3B3.9 GB42 tok/s203K ctx
dense
Ministral 3 3B Instruct 2512
C50
3B3.9 GB42 tok/s203K ctx
dense
HELVETE 3B
C50
3B3.9 GB42 tok/s203K ctx
dense
Hermes 3 Llama 3.2 3B
C50
3B3.9 GB42 tok/s203K ctx
dense
stablelm zephyr 3b
C50
3B3.9 GB42 tok/s203K ctx
dense
👁 Unsloth
Qwen3.5 9B
C50
9B8.2 GB22 tok/s12K ctx
dense
StarCoder2 3B
C50
3B3.9 GB42 tok/s203K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C50
9B8.2 GB22 tok/s12K ctx
dense
AI21 Jamba Reasoning 3B
C50
3B3.9 GB42 tok/s203K ctx
dense
Qwen3.5 9B
C49
9B8.2 GB22 tok/s12K ctx
dense
stablelm 3b 4e1t
C49
3B3.9 GB42 tok/s203K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C49
3B3.9 GB42 tok/s203K ctx
dense
ai21labs AI21 Jamba2 3B
C49
3B3.9 GB42 tok/s203K ctx
dense
Yi Coder 9B Chat
C49
9B8.2 GB22 tok/s12K ctx
dense
HelpingAI 3B hindi i1
C49
3B3.9 GB42 tok/s203K ctx
dense
AI21 Jamba2 3B
C49
3B3.9 GB42 tok/s203K ctx
dense
glm 4 9b chat 1m
C49
9B8.2 GB22 tok/s12K ctx
dense
HelpingAI 3B hindi
C49
3B3.9 GB42 tok/s203K ctx
dense
AI21 Jamba2 3B i1
C49
3B3.9 GB42 tok/s203K ctx
dense
Yi 1.5 9B Chat
C49
9B8.2 GB22 tok/s12K ctx
dense
👁 Mistral
Ministral 8B
C49
8B8.8 GB23 tok/s10K ctx
dense
Yi 9B Coder i1
C49
9B8.2 GB22 tok/s12K ctx
dense
HelpingAI2 9B
C49
9B8.2 GB22 tok/s12K ctx
dense
HelpingAI2 9B i1
C49
9B8.2 GB22 tok/s12K ctx
dense
HelpingAI 9B 200k i1
C49
9B8.2 GB22 tok/s12K ctx
dense
HelpingAI 9B i1
C49
9B8.2 GB22 tok/s12K ctx
dense
👁 BigCode
StarCoder2 3B
C49
3B4.0 GB42 tok/s16K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C49
0.5B2.2 GB7 tok/s131K ctx
dense
👁 Alibaba
Qwen 3 0.6B
C48
0.6B2.9 GB8 tok/s33K ctx
dense
gemma 2 2b it
C48
2B3.6 GB28 tok/s318K ctx
dense
👁 Meta
Llama 3.2 1B
C48
1B2.8 GB14 tok/s128K ctx
dense
EXAONE 3.5 2.4B Instruct
C48
2.4B3.4 GB34 tok/s275K ctx
dense
👁 Google
gemma 2b
C47
2B3.2 GB28 tok/s347K ctx
dense
Gemmasutra Mini 2B v1
C47
2B3.2 GB28 tok/s347K ctx
dense
gemma 2 2b it
C47
2B3.2 GB28 tok/s347K ctx
dense
👁 Alibaba
Qwen 3.5 0.6B
C46
0.6B2.9 GB8 tok/s111K ctx
dense
👁 Qwen
Qwen2.5 1.5B Instruct
C45
1.5B2.8 GB21 tok/s490K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B
C45
1.5B2.8 GB21 tok/s490K ctx
dense
Yi Coder 1.5B Chat
C45
1.5B2.8 GB21 tok/s490K ctx
dense
stablelm 2 zephyr 1.6b
C45
1.6B2.9 GB22 tok/s454K ctx
dense
logos16v2 stablelm2 1.6b i1
C45
1.6B2.9 GB22 tok/s454K ctx
dense
👁 IBM
Granite 3.1 8B
C45
8B8.5 GB28 tok/s12K ctx
state-space
Yi Coder 1.5B
C44
1.5B2.8 GB21 tok/s490K ctx
dense
👁 Unsloth
Falcon H1 1.5B Instruct
C44
1.5B2.8 GB21 tok/s490K ctx
dense
👁 01.AI
Yi 1.5 9B
C44
9B8.7 GB21 tok/s4K ctx
dense
EXAONE 4.0 1.2B
C43
1.2B2.6 GB17 tok/s634K ctx
dense
Llama 3.2 1B Instruct Q8 0
C43
1B2.6 GB14 tok/s748K ctx
dense
TinyLlama 1.1B Chat v1.0
C43
1.1B2.5 GB15 tok/s699K ctx
dense
TinyLlama 1.1B Chat v0.3
C43
1.1B2.5 GB15 tok/s699K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
C43
1.1B2.5 GB15 tok/s699K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
C42
1.1B2.5 GB15 tok/s699K ctx
dense
Llama 3.2 1B Instruct
C42
1B2.4 GB14 tok/s777K ctx
dense
gemma 3 1b it
C42
1B2.4 GB14 tok/s777K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
C42
0.5B2.2 GB7 tok/s131K ctx
dense
Falcon3 1B Instruct abliterated
C42
1B2.4 GB14 tok/s777K ctx
dense
👁 Cohere
Aya Expanse 8B
C41
8B8.5 GB25 tok/s8K ctx
dense
8B8.5 GB25 tok/s12K ctx
dense
F

F Tier -- Can't Run (179 models)

Too heavy for this hardware.

SmolVLM 500M Instruct
D40
0.5B2.2 GB7 tok/s942K ctx
dense
embeddinggemma 300M
D38
0.3B2.0 GB4 tok/s969K ctx
dense
HelpingAI2.5 10B i1
D38
10B9.0 GB16 tok/s4K ctx
dense
Helply 10.2b chat i1
D38
10.2B9.1 GB16 tok/s4K ctx
dense
granite embedding 107m multilingual
D35
0.11B1.9 GB2 tok/s998K ctx
dense
Falcon H1 Tiny 90M Instruct
D35
0.09B1.9 GB2 tok/s999K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
D32
10.7B9.5 GB14 tok/s4K ctx
dense
Nous Hermes 2 SOLAR 10.7B
D32
10.7B9.5 GB14 tok/s4K ctx
dense
solar finalised finetuned Model 10.7B i1
D31
10.7B9.5 GB14 tok/s4K ctx
dense
SOLAR 10.7B v1.0
D31
10.7B9.5 GB14 tok/s4K ctx
dense
👁 Meta
Llama 3.1 70B
F0
70B49.3 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.3 70B
F0
70B49.3 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.2 11B Vision
F0
11B10.4 GB12 tok/s4K ctx
vision
👁 Alibaba
Qwen 2.5 14B
F0
14B13.2 GB6 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 32B
F0
32B25.1 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 72B
F0
72B50.5 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 14B
F0
14B13.2 GB6 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 32B
F0
32B25.1 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 14B
F0
14B12.7 GB6 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 32B
F0
32B25.1 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
F0
235B147.9 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3 30B A3B
F0
30.5B21.8 GB4 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 30B A3B Instruct
F0
30.5B21.8 GB4 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder-Next
F0
80B52.0 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B297.4 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-VL 30B A3B Instruct
F0
30B21.5 GB4 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 27B
F0
27B21.3 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3.5 35B A3B
F0
35B24.5 GB4 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.6 35B A3B
F0
35B27.2 GB3 tok/s4K ctx
+1moe
👁 Alibaba
Qwen 3.6 27B
F0
27B19.1 GB2 tok/s4K ctx
+1dense
👁 Alibaba
Qwen 3.5 122B A10B
F0
122B78.6 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B246.7 GB2 tok/s4K ctx
moe
👁 Google
Gemma 2 9B
F0
9B12.3 GB7 tok/s4K ctx
dense
👁 Google
Gemma 2 27B
F0
27B29.4 GB2 tok/s4K ctx
dense
👁 Google
Gemma 3 12B
F0
12B13.9 GB4 tok/s4K ctx
dense
👁 Google
Gemma 3 27B
F0
27B29.4 GB2 tok/s4K ctx
dense
👁 Mistral
Ministral 3 14B
F0
14B12.7 GB6 tok/s4K ctx
multimodal
👁 Mistral
Mistral Nemo 12B
F0
12B11.5 GB9 tok/s4K ctx
dense
👁 Mistral
Mistral Small 24B
F0
24B18.8 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 3.2 24B
F0
24B18.8 GB2 tok/s4K ctx
vision
👁 Mistral
Mixtral 8x7B
F0
47B32.3 GB2 tok/s4K ctx
moe
👁 Mistral
Mixtral 8x22B
F0
141B91.1 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 Distill 14B
F0
14B13.2 GB6 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 32B
F0
32B25.1 GB2 tok/s4K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
F0
4B10.0 GB33 tok/s11K ctx
dense
F0
14B13.3 GB6 tok/s4K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
F0
14.7B13.7 GB5 tok/s4K ctx
dense
👁 IBM
Granite 4.1 30B
F0
30B23.9 GB2 tok/s4K ctx
dense
👁 AllenAI
OLMo 2 13B
F0
13B12.1 GB7 tok/s4K ctx
dense
👁 Cohere
Command R 35B
F0
35B25.5 GB2 tok/s4K ctx
dense
👁 TII
Falcon 40B Instruct
F0
40B32.3 GB2 tok/s4K ctx
dense
👁 WizardLM
WizardLM 13B
F0
13B21.8 GB3 tok/s4K ctx
dense
👁 BigCode
StarCoder 7B
F0
7B13.3 GB10 tok/s4K ctx
dense
👁 BigCode
StarCoder 15B
F0
15B27.1 GB2 tok/s4K ctx
dense
👁 Meta
CodeLlama 7B Instruct
F0
7B13.8 GB10 tok/s4K ctx
dense
👁 Meta
CodeLlama 13B Instruct
F0
13B21.8 GB3 tok/s4K ctx
dense
👁 BigCode
StarCoder2 15B
F0
15B13.7 GB4 tok/s4K ctx
dense
👁 MosaicML
MPT-7B-Instruct
F0
7B13.8 GB10 tok/s4K ctx
dense
👁 MosaicML
MPT-30B-Instruct
F0
30B46.7 GB2 tok/s4K ctx
dense
👁 InternLM
InternLM 7B
F0
7B13.8 GB10 tok/s4K ctx
dense
👁 InternLM
InternLM Chat 7B
F0
7B13.8 GB10 tok/s4K ctx
dense
👁 Mistral
Devstral Small 1.1
F0
24B18.8 GB2 tok/s4K ctx
dense
👁 Mistral
Devstral Small 2 24B Instruct
F0
24B18.8 GB2 tok/s4K ctx
dense
👁 Mistral
Devstral 2 123B Instruct
F0
123B82.1 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 4 119B
F0
119B79.7 GB2 tok/s4K ctx
moe
👁 Mistral
Leanstral 119B A6B
F0
119B83.1 GB2 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B418.8 GB2 tok/s4K ctx
+1moe
👁 Mistral
Magistral Small 2507
F0
24B18.8 GB2 tok/s4K ctx
dense
👁 Mistral
Codestral 2 25.08
F0
22B17.6 GB2 tok/s4K ctx
dense
F0
744B474.6 GB2 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B480.7 GB2 tok/s4K ctx
moe
F0
1000B619.1 GB2 tok/s4K ctx
moe
F0
1000B619.1 GB2 tok/s4K ctx
+1moe
👁 Moonshot AI
Kimi Linear 48B A3B
F0
48B31.9 GB2 tok/s4K ctx
linear
👁 Nous Research
Nous Hermes 1.0
F0
9B19.4 GB5 tok/s4K ctx
dense
👁 Nous Research
Nous Dolphin 13B
F0
13B23.3 GB3 tok/s4K ctx
dense
👁 Baichuan
Baichuan 7B
F0
7B13.8 GB10 tok/s4K ctx
dense
👁 Baichuan
Baichuan 13B
F0
13B23.3 GB3 tok/s4K ctx
dense
👁 Cerebras
Cerebras-GPT 13B
F0
13B20.8 GB3 tok/s4K ctx
dense
👁 Stability AI
StableLM 2 12B
F0
12B22.5 GB3 tok/s4K ctx
dense
👁 InternLM
InternLM 20B
F0
20B34.4 GB2 tok/s4K ctx
dense
👁 01.AI
Yi 34B Chat
F0
34B26.1 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3 671B
F0
671B470.6 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B470.6 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B865.6 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Flash
F0
284B161.0 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B470.6 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 16B
F0
16B14.8 GB9 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B204.3 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B204.3 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek LLM 7B
F0
7B13.3 GB10 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek LLM 67B
F0
67B48.4 GB2 tok/s4K ctx
dense
👁 Meta
Llama 4 Scout 17B 16E
F0
109B71.1 GB2 tok/s4K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B248.6 GB2 tok/s4K ctx
moe
👁 Cohere
Command R+ 104B
F0
104B68.6 GB2 tok/s4K ctx
dense
👁 Cohere
Command A 111B
F0
111B73.3 GB2 tok/s4K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
F0
3.8B9.9 GB35 tok/s11K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
F0
14B13.3 GB6 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 34B
F0
34B26.1 GB2 tok/s4K ctx
dense
👁 Mistral AI
Codestral 22B
F0
22B17.6 GB2 tok/s4K ctx
dense
👁 Mistral AI
Pixtral 12B
F0
12B11.5 GB9 tok/s4K ctx
dense
👁 Mistral AI
Pixtral Large 124B
F0
124B82.7 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 VL 72B
F0
72B50.5 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
F0
72B50.5 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 70B
F0
70B49.3 GB2 tok/s4K ctx
dense
👁 LLaVA
LLaVA 1.5 7B
F0
7B13.8 GB10 tok/s4K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
F0
13B21.8 GB3 tok/s4K ctx
dense
F0
19B15.7 GB3 tok/s4K ctx
dense
👁 LMSYS
Vicuna 7B
F0
7B13.8 GB10 tok/s4K ctx
dense
👁 LMSYS
Vicuna 13B
F0
13B21.8 GB3 tok/s4K ctx
dense
👁 IBM
Granite Code 20B
F0
20B17.1 GB2 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 20B
F0
21B17.0 GB5 tok/s4K ctx
moe
👁 Allen AI
OLMo 2 32B
F0
32B25.1 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron Nano 9B v2
F0
9B9.6 GB17 tok/s5K ctx
dense
👁 NVIDIA
Nemotron 3 Nano 30B
F0
30B22.4 GB2 tok/s4K ctx
dense
👁 LG AI
EXAONE 4.0 32B
F0
32B25.1 GB2 tok/s4K ctx
dense
F0
24B18.8 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.1 405B
F0
405B256.4 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
F0
70B49.3 GB2 tok/s4K ctx
dense
👁 IBM
Granite Code 34B
F0
34B26.1 GB2 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 120B
F0
117B78.0 GB2 tok/s4K ctx
dense
👁 Cohere
Aya Expanse 32B
F0
32B23.7 GB2 tok/s4K ctx
dense
👁 Mistral AI
Mistral Small 3.1 24B
F0
24B18.8 GB2 tok/s4K ctx
dense
👁 Google
Gemma 4 26B A4B
F0
25.2B20.7 GB4 tok/s4K ctx
moe
👁 Google
Gemma 4 31B
F0
30.7B35.1 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B411.5 GB2 tok/s4K ctx
moe
👁 NVIDIA
Nemotron Cascade 2 30B A3B
F0
30B22.9 GB4 tok/s4K ctx
moe
MiniMax M2.7
F0
230B145.8 GB2 tok/s4K ctx
moe
Solar Open 100B
F0
100B74.4 GB2 tok/s4K ctx
dense
Baichuan M2 32B Q4 K M
F0
32B25.0 GB2 tok/s4K ctx
dense
baichuan inc Baichuan M2 32B
F0
32B25.0 GB2 tok/s4K ctx
dense
Codestral 22B v0.1
F0
22B17.7 GB2 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B19.2 GB2 tok/s4K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
F0
24B19.2 GB2 tok/s4K ctx
dense
internlm JanusCoder 14B
F0
14B11.9 GB7 tok/s4K ctx
dense
internlm2 5 20b chat
F0
20B16.2 GB2 tok/s4K ctx
dense
NousResearch Hermes 4 14B
F0
14B11.9 GB7 tok/s4K ctx
dense
starcoder2 15b instruct v0.1
F0
15B12.6 GB5 tok/s4K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
F0
48B36.6 GB2 tok/s4K ctx
dense
internlm2 limarp chat 20b
F0
20B16.2 GB2 tok/s4K ctx
dense
Phi 4 reasoning vision 15B
F0
15B12.6 GB5 tok/s4K ctx
dense
Codestral 22B v0.1 IMat
F0
22B17.7 GB2 tok/s4K ctx
dense
EXAONE 4.0 32B
F0
32B25.0 GB2 tok/s4K ctx
dense
K EXAONE 236B A23B
F0
236B173.3 GB2 tok/s4K ctx
dense
Codestral 22B v0.1
F0
22B17.7 GB2 tok/s4K ctx
dense
Qwen3.5 35B A3B
F0
35B27.2 GB2 tok/s4K ctx
dense
starcoder2 15b instruct v0.1
F0
15B12.6 GB5 tok/s4K ctx
dense
gemma 3 12b it
F0
12B10.4 GB10 tok/s4K ctx
dense
gemma 3 27b it
F0
27B21.3 GB2 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F0
70B52.6 GB2 tok/s4K ctx
dense
Mistral Small 24B Instruct 2501
F0
24B19.2 GB2 tok/s4K ctx
dense
mistral small 3.1 24b instruct 2503 hf
F0
24B19.2 GB2 tok/s4K ctx
dense
aya expanse 32b heretic MPOA i1
F0
32B25.0 GB2 tok/s4K ctx
dense
Baichuan M3 235B
F0
235B172.6 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0
235B172.6 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F0
72B54.1 GB2 tok/s4K ctx
dense
Codestral 21B Pruned i1
F0
21B17.0 GB2 tok/s4K ctx
dense
Codestral 22B v0.1 i1
F0
22B17.7 GB2 tok/s4K ctx
dense
Codestral RAG 19B Pruned i1
F0
19B15.5 GB3 tok/s4K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
F0
24B19.2 GB2 tok/s4K ctx
dense
HelpingAI 15B i1
F0
15B12.6 GB5 tok/s4K ctx
dense
internlm2 math plus 20b i1
F0
20B16.2 GB2 tok/s4K ctx
dense
Solar Open 100B i1
F0
100B74.4 GB2 tok/s4K ctx
dense
Solar Open 69B REAP i1
F0
69B51.9 GB2 tok/s4K ctx
dense
starcoder2 15b i1
F0
15B12.6 GB5 tok/s4K ctx
dense
Hermes 4.3 36B
F0
36B27.9 GB2 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F0
70B52.6 GB2 tok/s4K ctx
dense
Codestral 22B v0.1
F0
22B17.7 GB2 tok/s4K ctx
dense
StarCoder2 15B
F0
15B12.6 GB5 tok/s4K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
F0
14B11.9 GB7 tok/s4K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
F0
14B11.9 GB7 tok/s4K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
F0
14B11.9 GB7 tok/s4K ctx
dense
👁 Unsloth
gemma 3 27b it
F0
27B21.3 GB2 tok/s4K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
F0
24B19.2 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
F0
122B75.8 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 27B
F0
27B21.3 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
F0
35B27.2 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 397B A17B
F0
397B290.4 GB2 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B19.2 GB2 tok/s4K ctx
dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

RTX 3050 8GB

8 GB VRAM

View tier list

RTX 3060 Ti 8GB

8 GB VRAM

View tier list

RTX 3070 8GB

8 GB VRAM

View tier list

RTX 4060 8GB

8 GB VRAM

View tier list
Full Radeon RX 7700S 8GB pageCompare this hardware