VOOZH about

URL: https://willitrunai.com/my-results/rtx-4500-ada-24gb

⇱ RTX 4500 Ada 24GB AI Tier List: 295 models ranked | WillItRunAI


AI Compatibility Tier List

RTX 4500 Ada 24GB

374 AI models ranked by how well they run on your 24 GB VRAM hardware. Best match: Qwen3-Coder 30B A3B Instruct (score: 95).

374

Models tested

295

Can run

24 GB

VRAM

52

Best tok/s

Tier Distribution

S 21
A 58
B 39
C 177
F 79
S: 21A: 58B: 39C: 177F: 79
S

S Tier -- Perfect Fit (21 models)

These models run flawlessly with headroom to spare.

👁 Alibaba
Qwen3-Coder 30B A3B Instruct
S95
30.5B23.4 GB52 tok/s23K ctx
moe
👁 Alibaba
Qwen3-VL 30B A3B Instruct
S94
30B23.1 GB53 tok/s26K ctx
moe
👁 OpenAI
GPT-OSS 20B
S94
21B18.6 GB66 tok/s52K ctx
moe
👁 Alibaba
Qwen 3 14B
S93
14B14.3 GB43 tok/s80K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
S93
14.7B15.3 GB41 tok/s33K ctx
dense
👁 Alibaba
Qwen 3 30B A3B
S93
30.5B23.4 GB52 tok/s23K ctx
moe
👁 Alibaba
Qwen 3.5 9B
S92
9B11.0 GB67 tok/s111K ctx
dense
👁 Alibaba
Qwen 3.5 27B
S92
27B22.9 GB22 tok/s21K ctx
dense
👁 Mistral
Magistral Small 2507
S91
24B20.4 GB25 tok/s40K ctx
dense
👁 Mistral
Devstral Small 2 24B Instruct
S91
24B20.4 GB25 tok/s40K ctx
dense
👁 Alibaba
Qwen 3.6 27B
S91
27B20.7 GB17 tok/s69K ctx
+1dense
👁 Alibaba
Qwen 3 8B
S90
8B10.4 GB75 tok/s115K ctx
dense
👁 Mistral
Devstral Small 1.1
S89
24B20.4 GB25 tok/s40K ctx
dense
👁 NVIDIA
Nemotron Cascade 2 30B A3B
S89
30B24.5 GB38 tok/s13K ctx
moe
👁 NVIDIA
Nemotron 3 Nano 30B
S88
30B24.0 GB15 tok/s16K ctx
dense
👁 Alibaba
Qwen 3.5 4B
S87
4B7.9 GB56 tok/s131K ctx
dense
👁 Google
Gemma 4 26B A4B
S87
25.2B22.3 GB55 tok/s23K ctx
moe
👁 Mistral
Ministral 3 14B
S87
14B14.3 GB43 tok/s80K ctx
multimodal
👁 Mistral
Codestral 2 25.08
S87
22B19.2 GB24 tok/s48K ctx
dense
S87
19B17.3 GB32 tok/s8K ctx
dense
👁 NVIDIA
Nemotron Nano 8B
S85
8B10.1 GB75 tok/s130K ctx
dense
A

A Tier -- Great Fit (58 models)

Excellent performance with comfortable memory margins.

👁 DeepSeek
DeepSeek Coder V2 16B
A85
16B16.4 GB83 tok/s53K ctx
moe
A84
14B14.9 GB43 tok/s16K ctx
dense
👁 Mistral
Mistral Small 3.2 24B
A84
24B20.4 GB25 tok/s40K ctx
vision
👁 Microsoft
Phi-4 Mini Reasoning 4B
A84
3.8B7.1 GB53 tok/s131K ctx
dense
👁 Alibaba
Qwen 2.5 14B
A83
14B14.8 GB43 tok/s66K ctx
dense
A83
24B20.4 GB25 tok/s40K ctx
dense
👁 IBM
Granite Code 20B
A83
20B18.7 GB30 tok/s8K ctx
dense
👁 InternLM
InternVL2 8B
A83
8B10.1 GB75 tok/s8K ctx
dense
👁 Google
Gemma 3 12B
A82
12B15.5 GB37 tok/s44K ctx
dense
👁 Alibaba
Qwen 3.5 35B A3B
A82
35B26.1 GB30 tok/s4K ctx
moe
👁 Mistral
Mistral Small 24B
A82
24B20.4 GB25 tok/s33K ctx
dense
👁 Mistral
Ministral 3 8B
A81
8B10.4 GB75 tok/s115K ctx
multimodal
👁 Mistral AI
Mistral Small 3.1 24B
A81
24B20.4 GB25 tok/s40K ctx
dense
👁 OpenBMB
MiniCPM-V 2.6 8B
A81
8B10.1 GB75 tok/s2K ctx
dense
👁 NVIDIA
Nemotron Nano 9B v2
A80
9B11.2 GB67 tok/s100K ctx
dense
👁 Defog
SQLCoder 7B
A80
7B9.5 GB86 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 VL 7B
A79
7B8.4 GB87 tok/s33K ctx
dense
👁 AllenAI
OLMo 2 13B
A79
13B13.7 GB47 tok/s33K ctx
dense
👁 Alibaba
Qwen 3 4B
A79
4B7.9 GB56 tok/s33K ctx
dense
👁 Meta
CodeLlama 7B Instruct
A79
7B15.4 GB80 tok/s16K ctx
dense
👁 Alibaba
Qwen 3 32B
A78
32B26.7 GB11 tok/s5K ctx
dense
👁 BigCode
StarCoder 7B
A78
7B14.9 GB80 tok/s8K ctx
dense
👁 Magistral AI
Magistral 7B
A78
7B9.5 GB86 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 14B
A77
14B14.8 GB43 tok/s33K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
A77
9B9.4 GB68 tok/s131K ctx
dense
👁 Jina AI
Jina Embeddings v3
A77
0.57B6.4 GB8 tok/s8K ctx
dense
👁 Meta
CodeLlama 13B Instruct
A77
13B23.4 GB43 tok/s16K ctx
dense
👁 Google
Gemma 4 E4B
A76
8B9.5 GB57 tok/s128K ctx
dense
👁 InternLM
InternLM 7B
A76
7B15.4 GB80 tok/s8K ctx
dense
👁 InternLM
InternLM Chat 7B
A76
7B15.4 GB80 tok/s8K ctx
dense
👁 Alibaba
Qwen 3.6 35B A3B
A76
35B28.8 GB22 tok/s4K ctx
+1moe
👁 IBM
Granite Code 8B
A75
8B10.1 GB75 tok/s8K ctx
dense
👁 DevStral AI
DevStral 7B
A75
7B9.5 GB86 tok/s8K ctx
dense
👁 Mistral AI
Pixtral 12B
A75
12B13.1 GB50 tok/s88K ctx
dense
👁 Alibaba
Qwen 2.5 7B
A75
7B8.4 GB87 tok/s131K ctx
dense
👁 BAAI
BGE M3
A75
0.57B5.6 GB8 tok/s8K ctx
dense
👁 IBM
Granite 4.1 8B
A75
8B10.6 GB75 tok/s104K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
A75
13B23.4 GB43 tok/s4K ctx
dense
👁 Mistral AI
Codestral Mamba 7B
A74
7B8.1 GB92 tok/s262K ctx
state-space
👁 Nous Research
Nous Hermes 1.0
A73
9B21.0 GB62 tok/s16K ctx
dense
👁 LLaVA
LLaVA 1.5 7B
A73
7B15.4 GB80 tok/s4K ctx
dense
👁 LG AI
EXAONE 4.0 32B
A72
32B26.7 GB11 tok/s5K ctx
dense
👁 WizardLM
WizardLM 13B
A72
13B23.4 GB43 tok/s8K ctx
dense
👁 LMSYS
Vicuna 13B
A72
13B23.4 GB43 tok/s4K ctx
dense
A72
7B10.5 GB86 tok/s8K ctx
dense
👁 Mixedbread AI
mxbai Embed Large
A72
0.34B5.5 GB5 tok/s1K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 3B
A72
3B7.3 GB42 tok/s131K ctx
dense
👁 MosaicML
MPT-7B-Instruct
A71
7B15.4 GB80 tok/s8K ctx
dense
👁 Baichuan
Baichuan 7B
A71
7B15.4 GB80 tok/s8K ctx
dense
👁 Meta
Llama 3.1 8B
A71
8B10.1 GB75 tok/s128K ctx
dense
👁 WizardLM
WizardMath 7B
A71
7B9.5 GB86 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
A71
7B9.5 GB86 tok/s4K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
A71
0.34B5.5 GB5 tok/s1K ctx
dense
👁 Alibaba
Qwen 2.5 32B
A71
32B26.7 GB11 tok/s5K ctx
dense
👁 Zhipu
GLM-4 9B
A71
9B9.4 GB68 tok/s128K ctx
dense
👁 Nous Research
Nous Dolphin 13B
A70
13B24.9 GB26 tok/s15K ctx
dense
👁 Google
Gemma 4 E2B
A70
5.1B6.9 GB71 tok/s128K ctx
dense
👁 IBM
Granite 4.1 30B
A70
30B25.5 GB13 tok/s10K ctx
dense
B

B Tier -- Good Fit (39 models)

Solid performance, may need quantization or reduced context.

👁 Allen AI
OLMo 2 32B
B70
32B26.7 GB11 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 7B
B69
7B8.4 GB87 tok/s131K ctx
dense
👁 BAAI
BGE Large EN v1.5
B69
0.34B5.5 GB5 tok/s1K ctx
dense
👁 Google
Gemma 3 4B
B69
4B7.8 GB56 tok/s128K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
B67
3.8B11.5 GB53 tok/s50K ctx
dense
👁 Microsoft
Phi 4 Mini 4B
B67
4B7.2 GB56 tok/s128K ctx
dense
👁 Cerebras
Cerebras-GPT 13B
B67
13B22.4 GB37 tok/s19K ctx
dense
👁 Mistral
Ministral 3 3B
B67
3B5.9 GB42 tok/s262K ctx
multimodal
👁 Alibaba
Qwen 2.5 Coder 14B
B67
14B14.8 GB43 tok/s66K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 8B
B67
8B10.1 GB75 tok/s33K ctx
dense
👁 Google
Gemma 2 9B
B67
9B13.9 GB50 tok/s8K ctx
dense
👁 Nomic AI
Nomic Embed Text v1.5
B67
0.14B4.1 GB2 tok/s8K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
B66
4B11.6 GB56 tok/s50K ctx
dense
7B9.5 GB86 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 7B
B66
7B8.4 GB87 tok/s33K ctx
dense
👁 Baichuan
Baichuan 13B
B66
13B24.9 GB26 tok/s8K ctx
dense
👁 Alibaba
Qwen 3.5 2B
B66
2B6.2 GB28 tok/s131K ctx
dense
👁 Meta
Llama 3.2 11B Vision
B65
11B12.0 GB55 tok/s16K ctx
vision
👁 Alibaba
Qwen 2.5 Coder 32B
B65
32B26.7 GB11 tok/s5K ctx
dense
👁 TII
Falcon 7B Instruct
B65
7B7.7 GB88 tok/s8K ctx
dense
👁 Alibaba
Qwen 2.5 3B
B65
3B7.3 GB42 tok/s131K ctx
dense
👁 Mistral
Mistral Nemo 12B
B64
12B13.1 GB50 tok/s88K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
B64
14B14.9 GB43 tok/s64K ctx
dense
👁 IBM
Granite Code 34B
B64
34B27.7 GB10 tok/s4K ctx
dense
👁 Cohere
Command R 35B
B63
35B27.1 GB10 tok/s4K ctx
dense
👁 Mistral AI
Codestral 22B
B63
22B19.2 GB26 tok/s33K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B63
1.7B6.0 GB24 tok/s33K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 32B
B63
32B26.7 GB11 tok/s5K ctx
dense
👁 Mistral
Mistral 7B Instruct v0.3
B62
7B9.5 GB86 tok/s8K ctx
dense
👁 01.AI
Yi Coder 9B
B62
9B10.3 GB68 tok/s131K ctx
dense
👁 IBM
Granite Code 3B
B62
3B7.6 GB42 tok/s8K ctx
dense
👁 IBM
Granite 4.1 3B
B62
3B6.4 GB42 tok/s131K ctx
dense
B61
0.02B3.6 GB2 tok/s0K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 1.5B
B60
1.5B4.6 GB21 tok/s33K ctx
dense
👁 Mistral
Ministral 8B
B60
8B10.4 GB75 tok/s115K ctx
dense
👁 Meta
Llama 3.2 3B
B58
3B6.8 GB42 tok/s128K ctx
dense
👁 BigCode
StarCoder 15B
B57
15B28.7 GB17 tok/s8K ctx
dense
👁 LMSYS
Vicuna 7B
B56
7B15.4 GB80 tok/s4K ctx
dense
👁 IBM
Granite 3.1 8B
B55
8B10.1 GB87 tok/s128K ctx
state-space
C

C Tier -- Tight Fit (177 models)

Runs with offloading or significant compromises.

👁 01.AI
Yi 1.5 9B
C55
9B10.3 GB68 tok/s4K ctx
dense
👁 BigCode
StarCoder2 15B
C54
15B15.3 GB35 tok/s16K ctx
dense
C53
3B7.1 GB42 tok/s128K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
C53
7B8.4 GB87 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek LLM 7B
C53
7B14.9 GB80 tok/s4K ctx
dense
👁 Cohere
Aya Expanse 32B
C53
32B25.3 GB13 tok/s8K ctx
dense
Codestral 22B v0.1
C53
22B19.3 GB25 tok/s45K ctx
dense
Codestral RAG 19B Pruned i1
C53
19B17.1 GB29 tok/s65K ctx
dense
Codestral 22B v0.1
C53
22B19.3 GB25 tok/s45K ctx
dense
internlm2 5 20b chat
C53
20B17.8 GB28 tok/s58K ctx
dense
internlm2 limarp chat 20b
C53
20B17.8 GB28 tok/s58K ctx
dense
internlm2 math plus 20b i1
C53
20B17.8 GB28 tok/s58K ctx
dense
Codestral 22B v0.1
C52
22B19.3 GB25 tok/s45K ctx
dense
Codestral 21B Pruned i1
C52
21B18.6 GB27 tok/s51K ctx
dense
Codestral 22B v0.1 IMat
C52
22B19.3 GB25 tok/s45K ctx
dense
Codestral 22B v0.1 i1
C52
22B19.3 GB25 tok/s45K ctx
dense
👁 OpenChat
OpenChat 7B
C52
7B9.5 GB86 tok/s8K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
C52
1.5B4.6 GB21 tok/s33K ctx
dense
👁 Cohere
Aya Expanse 8B
C52
8B10.1 GB75 tok/s8K ctx
dense
👁 TinyLlama
TinyLlama 1.1B
C52
1.1B4.3 GB15 tok/s4K ctx
dense
Phi 4 reasoning vision 15B
C52
15B14.2 GB37 tok/s105K ctx
dense
StarCoder2 15B
C52
15B14.2 GB37 tok/s105K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
C51
14B13.5 GB40 tok/s119K ctx
dense
starcoder2 15b instruct v0.1
C51
15B14.2 GB37 tok/s105K ctx
dense
starcoder2 15b i1
C51
15B14.2 GB37 tok/s105K ctx
dense
starcoder2 15b instruct v0.1
C51
15B14.2 GB37 tok/s105K ctx
dense
HelpingAI 15B i1
C51
15B14.2 GB37 tok/s105K ctx
dense
NousResearch Hermes 4 14B
C51
14B13.5 GB40 tok/s119K ctx
dense
👁 Teknium
OpenHermes 2.5 7B
C51
7B9.5 GB86 tok/s8K ctx
dense
8B10.1 GB75 tok/s33K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
C51
14B13.5 GB40 tok/s119K ctx
dense
internlm JanusCoder 14B
C51
14B13.5 GB40 tok/s119K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
C51
14B13.5 GB40 tok/s119K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
C51
7B9.5 GB86 tok/s33K ctx
dense
gemma 3 12b it
C51
12B12.0 GB47 tok/s152K ctx
dense
👁 UC Berkeley
Starling LM 7B
C50
7B9.5 GB86 tok/s8K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C50
10.7B11.1 GB52 tok/s181K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C50
10.7B11.1 GB52 tok/s181K ctx
dense
👁 Unsloth
Qwen3.5 9B
C50
9B9.8 GB62 tok/s231K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C50
9B9.8 GB62 tok/s231K ctx
dense
👁 Stability AI
StableLM 2 12B
C50
12B24.1 GB27 tok/s4K ctx
dense
solar finalised finetuned Model 10.7B i1
C50
10.7B11.1 GB52 tok/s181K ctx
dense
Qwen3.5 9B
C50
9B9.8 GB62 tok/s231K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
C50
24B20.8 GB23 tok/s34K ctx
dense
SOLAR 10.7B v1.0
C50
10.7B11.1 GB52 tok/s181K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C50
24B20.8 GB23 tok/s34K ctx
dense
Mistral Small 24B Instruct 2501
C50
24B20.8 GB23 tok/s34K ctx
dense
Meta Llama 3.1 8B Instruct
C49
8B9.1 GB70 tok/s270K ctx
dense
👁 Unsloth
Qwen3.5 27B
C49
27B22.9 GB21 tok/s21K ctx
dense
mistral small 3.1 24b instruct 2503 hf
C49
24B20.8 GB23 tok/s34K ctx
dense
llava llama 3 8b v1 1
C49
8B9.1 GB70 tok/s270K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
C49
24B20.8 GB23 tok/s34K ctx
dense
Yi Coder 9B Chat
C49
9B9.8 GB62 tok/s231K ctx
dense
👁 Intel
Neural Chat 7B
C49
7B9.5 GB86 tok/s8K ctx
dense
glm 4 9b chat 1m
C49
9B9.8 GB62 tok/s231K ctx
dense
👁 01.AI
Yi 1.5 34B
C49
34B27.7 GB10 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
C49
1.5B4.6 GB21 tok/s131K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
C49
8B9.1 GB70 tok/s270K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
C49
24B20.8 GB23 tok/s34K ctx
dense
Meta Llama 3 8B Instruct
C49
8B9.1 GB70 tok/s270K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
C49
8B9.1 GB70 tok/s270K ctx
dense
👁 Unsloth
gemma 3 27b it
C49
27B22.9 GB21 tok/s21K ctx
dense
Dolphin3.0 Llama3.1 8B
C49
8B9.1 GB70 tok/s270K ctx
dense
Llama 3 8B Instruct 32k v0.1
C49
8B9.1 GB70 tok/s270K ctx
dense
Meta Llama 3.1 8B Instruct
C49
8B9.1 GB70 tok/s270K ctx
dense
vntl llama3 8b v2
C49
8B9.1 GB70 tok/s270K ctx
dense
Yi 1.5 9B Chat
C49
9B9.8 GB62 tok/s231K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C49
8B9.1 GB70 tok/s270K ctx
dense
Llama 2 7B Chat
C49
7B8.4 GB80 tok/s320K ctx
dense
Helply 10.2b chat i1
C49
10.2B10.7 GB55 tok/s194K ctx
dense
HelpingAI2.5 10B i1
C49
10B10.6 GB56 tok/s199K ctx
dense
falcon mamba 7b instruct Q4 K M
C49
7B8.4 GB92 tok/s320K ctx
dense
Mistral 7B Instruct v0.2
C49
7B8.4 GB80 tok/s320K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C49
8B9.1 GB70 tok/s270K ctx
dense
Mistral 7B Instruct v0.3
C49
7B8.4 GB80 tok/s320K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C49
8B9.1 GB70 tok/s270K ctx
dense
Hermes 3 Llama 3.1 8B
C49
8B9.1 GB70 tok/s270K ctx
dense
gemma 3 27b it
C49
27B22.9 GB21 tok/s21K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C49
24B20.8 GB23 tok/s34K ctx
dense
Hermes 2 Pro Llama 3 8B
C49
8B9.1 GB70 tok/s270K ctx
dense
Dolphin3.0 Llama3.1 8B
C49
8B9.1 GB70 tok/s270K ctx
dense
granite 8b code instruct 4k
C49
8B9.1 GB70 tok/s270K ctx
dense
Yi 9B Coder i1
C49
9B9.8 GB62 tok/s231K ctx
dense
dolphin 2.9.4 llama3.1 8b
C49
8B9.1 GB70 tok/s270K ctx
dense
Mamba Codestral 7B v0.1
C49
7B8.4 GB92 tok/s320K ctx
dense
HelpingAI2 9B
C49
9B9.8 GB62 tok/s231K ctx
dense
openchat 3.6 8b 20240522 IMat
C49
8B9.1 GB70 tok/s270K ctx
dense
Mistral 7B Instruct v0.3
C49
7B8.4 GB80 tok/s320K ctx
dense
Hermes 2 Pro Mistral 7B
C49
7B8.4 GB80 tok/s320K ctx
dense
EXAONE 3.5 7.8B Instruct
C49
7.8B9.0 GB72 tok/s279K ctx
dense
aya expanse 8b
C49
8B9.1 GB70 tok/s270K ctx
dense
zephyr 7B beta
C49
7B8.4 GB80 tok/s320K ctx
dense
HelpingAI2 9B i1
C49
9B9.8 GB62 tok/s231K ctx
dense
EXAONE 3.5 7.8B Instruct
C49
7.8B9.0 GB72 tok/s279K ctx
dense
dolphin v2 8b abliterated i1
C49
8B9.1 GB70 tok/s270K ctx
dense
HelpingAI 9B 200k i1
C49
9B9.8 GB62 tok/s231K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C49
7B8.4 GB80 tok/s320K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C49
7.8B9.0 GB72 tok/s279K ctx
dense
HelpingAI 9B i1
C49
9B9.8 GB62 tok/s231K ctx
dense
aya expanse 8b orthogonal heretic i1
C49
8B9.1 GB70 tok/s270K ctx
dense
Falcon H1R 7B
C49
7B8.4 GB80 tok/s320K ctx
dense
exaone 3.0 7.8b it
C49
7.8B9.0 GB72 tok/s279K ctx
dense
zephyr 7B alpha
C49
7B8.4 GB80 tok/s320K ctx
dense
speechless zephyr code functionary 7b
C49
7B8.4 GB80 tok/s320K ctx
dense
StarCoder2 7B
C49
7B8.4 GB80 tok/s320K ctx
dense
aya expanse 8b orthogonal heretic
C49
8B9.1 GB70 tok/s270K ctx
dense
japanese stablelm instruct gamma 7B
C49
7B8.4 GB80 tok/s320K ctx
dense
Falcon H1 7B Instruct
C49
7B8.4 GB80 tok/s320K ctx
dense
👁 Unsloth
Falcon H1R 7B
C49
7B8.4 GB80 tok/s320K ctx
dense
internlm2 5 1 8b chat i1
C49
8B9.1 GB70 tok/s270K ctx
dense
internlm3 8b instruct abliterated i1
C49
8B9.1 GB70 tok/s270K ctx
dense
stabilityai japanese stablelm base gamma 7b
C49
7B8.4 GB80 tok/s320K ctx
dense
Yi 1.5 6B Chat
C49
6B7.7 GB84 tok/s388K ctx
dense
baichuan2 7b chat
C49
7B8.4 GB80 tok/s320K ctx
dense
DiscoPOP zephyr 7b gemma
C49
7B8.4 GB80 tok/s320K ctx
dense
starcoder2 7b
C49
7B8.4 GB80 tok/s320K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C48
7B8.4 GB80 tok/s320K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C48
7B8.4 GB80 tok/s320K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C48
7B8.4 GB80 tok/s320K ctx
dense
internlm2 math plus 7b IMat
C48
7B8.4 GB80 tok/s320K ctx
dense
stablelm 2 zephyr 1 6b
C48
6B7.7 GB84 tok/s388K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C48
7B8.4 GB80 tok/s320K ctx
dense
👁 01.AI
Yi 1.5 6B
C48
6B7.9 GB84 tok/s4K ctx
dense
internlm2 5 7b chat i1
C48
7B8.4 GB80 tok/s320K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C48
7B8.4 GB80 tok/s320K ctx
dense
MD Judge v0 2 internlm2 7b i1
C48
7B8.4 GB80 tok/s320K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C48
7B8.4 GB80 tok/s320K ctx
dense
jointpreferences mistral 7b sft helpful
C48
7B8.4 GB80 tok/s320K ctx
dense
zephyr 7b dpo full i1
C48
7B8.4 GB80 tok/s320K ctx
dense
blossom v3 baichuan2 7b i1
C48
7B8.4 GB80 tok/s320K ctx
dense
blossom v1 baichuan 7b i1
C48
7B8.4 GB80 tok/s320K ctx
dense
Yi 1.5 6B Chat
C48
6B7.7 GB84 tok/s388K ctx
dense
stablelm 2 1 6b chat imatrix
C48
6B7.7 GB84 tok/s388K ctx
dense
👁 Google
Gemma 2 2B
C48
2B6.1 GB28 tok/s8K ctx
dense
👁 BigCode
StarCoder2 7B
C48
7B8.1 GB87 tok/s16K ctx
dense
HelpingAI2 6B
C48
6B7.7 GB84 tok/s388K ctx
dense
HelpingAI2 6B i1
C48
6B7.7 GB84 tok/s388K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
C48
4B7.7 GB56 tok/s4K ctx
dense
👁 Google
Gemma 3 1B
C48
1B4.3 GB14 tok/s33K ctx
dense
HelpingAI2.5 5B i1
C47
5B6.9 GB70 tok/s482K ctx
dense
👁 Unsloth
Qwen3.5 4B
C46
4B6.2 GB56 tok/s623K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C46
0.5B3.8 GB7 tok/s131K ctx
dense
gemma 3 4b it
C46
4B6.2 GB56 tok/s623K ctx
dense
gemma 3 4b it
C46
4B6.2 GB56 tok/s623K ctx
dense
Llama 3.2 3B Instruct
C45
3B5.8 GB42 tok/s844K ctx
dense
👁 Alibaba
Qwen 3 0.6B
C45
0.6B4.5 GB8 tok/s33K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C45
3B5.5 GB42 tok/s859K ctx
dense
👁 Meta
Llama 3.2 1B
C44
1B4.4 GB14 tok/s128K ctx
dense
Llama 3.2 3B Instruct
C44
3B5.5 GB42 tok/s859K ctx
dense
Ministral 3 3B Instruct 2512
C44
3B5.5 GB42 tok/s859K ctx
dense
HELVETE 3B
C44
3B5.5 GB42 tok/s859K ctx
dense
Hermes 3 Llama 3.2 3B
C44
3B5.5 GB42 tok/s859K ctx
dense
stablelm zephyr 3b
C44
3B5.5 GB42 tok/s859K ctx
dense
StarCoder2 3B
C44
3B5.5 GB42 tok/s859K ctx
dense
AI21 Jamba Reasoning 3B
C44
3B5.5 GB42 tok/s859K ctx
dense
stablelm 3b 4e1t
C44
3B5.5 GB42 tok/s859K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C44
3B5.5 GB42 tok/s859K ctx
dense
ai21labs AI21 Jamba2 3B
C44
3B5.5 GB42 tok/s859K ctx
dense
HelpingAI 3B hindi i1
C44
3B5.5 GB42 tok/s859K ctx
dense
AI21 Jamba2 3B
C44
3B5.5 GB42 tok/s859K ctx
dense
HelpingAI 3B hindi
C44
3B5.5 GB42 tok/s859K ctx
dense
AI21 Jamba2 3B i1
C44
3B5.5 GB42 tok/s859K ctx
dense
gemma 2 2b it
C43
2B5.2 GB28 tok/s1301K ctx
dense
EXAONE 3.5 2.4B Instruct
C43
2.4B5.0 GB34 tok/s1094K ctx
dense
👁 BigCode
StarCoder2 3B
C43
3B5.6 GB42 tok/s16K ctx
dense
👁 Google
gemma 2b
C43
2B4.8 GB28 tok/s1330K ctx
dense
Gemmasutra Mini 2B v1
C43
2B4.8 GB28 tok/s1330K ctx
dense
gemma 2 2b it
C42
2B4.8 GB28 tok/s1330K ctx
dense
👁 Alibaba
Qwen 3.5 0.6B
C42
0.6B4.5 GB8 tok/s131K ctx
dense
👁 Qwen
Qwen2.5 1.5B Instruct
C41
1.5B4.4 GB21 tok/s1801K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B
C41
1.5B4.4 GB21 tok/s1801K ctx
dense
Yi Coder 1.5B Chat
C41
1.5B4.4 GB21 tok/s1801K ctx
dense
stablelm 2 zephyr 1.6b
C41
1.6B4.5 GB22 tok/s1683K ctx
dense
logos16v2 stablelm2 1.6b i1
C41
1.6B4.5 GB22 tok/s1683K ctx
dense
Yi Coder 1.5B
C41
1.5B4.4 GB21 tok/s1801K ctx
dense
👁 Unsloth
Falcon H1 1.5B Instruct
C41
1.5B4.4 GB21 tok/s1801K ctx
dense
TinyLlama 1.1B Chat v1.0
C40
1.1B4.1 GB15 tok/s2486K ctx
dense
F

F Tier -- Can't Run (79 models)

Too heavy for this hardware.

EXAONE 4.0 1.2B
D40
1.2B4.2 GB17 tok/s2272K ctx
dense
Llama 3.2 1B Instruct Q8 0
D40
1B4.2 GB14 tok/s2714K ctx
dense
TinyLlama 1.1B Chat v0.3
D40
1.1B4.1 GB15 tok/s2486K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
D40
0.5B3.8 GB7 tok/s131K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
D40
1.1B4.1 GB15 tok/s2486K ctx
dense
Llama 3.2 1B Instruct
D40
1B4.0 GB14 tok/s2743K ctx
dense
gemma 3 1b it
D40
1B4.0 GB14 tok/s2743K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
D39
1.1B4.1 GB15 tok/s2486K ctx
dense
Falcon3 1B Instruct abliterated
D39
1B4.0 GB14 tok/s2743K ctx
dense
👁 01.AI
Yi 34B Chat
D38
34B27.7 GB10 tok/s4K ctx
dense
SmolVLM 500M Instruct
D37
0.5B3.8 GB7 tok/s3246K ctx
dense
EXAONE 4.0 32B
D37
32B26.6 GB11 tok/s5K ctx
dense
aya expanse 32b heretic MPOA i1
D37
32B26.6 GB11 tok/s5K ctx
dense
Baichuan M2 32B Q4 K M
D37
32B26.6 GB11 tok/s5K ctx
dense
baichuan inc Baichuan M2 32B
D37
32B26.6 GB11 tok/s5K ctx
dense
embeddinggemma 300M
D36
0.3B3.6 GB4 tok/s3273K ctx
dense
granite embedding 107m multilingual
D33
0.11B3.5 GB2 tok/s3302K ctx
dense
Falcon H1 Tiny 90M Instruct
D33
0.09B3.5 GB2 tok/s3303K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
D31
35B28.8 GB8 tok/s4K ctx
dense
Qwen3.5 35B A3B
D30
35B28.8 GB8 tok/s4K ctx
dense
👁 Meta
Llama 3.1 70B
F0
70B50.9 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.3 70B
F0
70B50.9 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 72B
F0
72B52.1 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
F0
235B149.5 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder-Next
F0
80B53.6 GB4 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B299.0 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 122B A10B
F0
122B80.2 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B248.3 GB2 tok/s4K ctx
moe
👁 Google
Gemma 2 27B
F0
27B31.0 GB7 tok/s6K ctx
dense
👁 Google
Gemma 3 27B
F0
27B31.0 GB7 tok/s6K ctx
dense
👁 Mistral
Mixtral 8x7B
F0
47B33.9 GB9 tok/s4K ctx
moe
👁 Mistral
Mixtral 8x22B
F0
141B92.7 GB2 tok/s4K ctx
moe
👁 TII
Falcon 40B Instruct
F0
40B33.9 GB5 tok/s4K ctx
dense
👁 MosaicML
MPT-30B-Instruct
F0
30B48.3 GB3 tok/s4K ctx
dense
👁 Mistral
Devstral 2 123B Instruct
F0
123B83.7 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 4 119B
F0
119B81.3 GB2 tok/s4K ctx
moe
👁 Mistral
Leanstral 119B A6B
F0
119B84.7 GB2 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B420.4 GB2 tok/s4K ctx
+1moe
F0
744B476.2 GB2 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B482.3 GB2 tok/s4K ctx
moe
F0
1000B620.7 GB2 tok/s4K ctx
moe
F0
1000B620.7 GB2 tok/s4K ctx
+1moe
👁 Moonshot AI
Kimi Linear 48B A3B
F0
48B33.5 GB4 tok/s4K ctx
linear
👁 InternLM
InternLM 20B
F0
20B36.0 GB8 tok/s6K ctx
dense
👁 DeepSeek
DeepSeek V3 671B
F0
671B472.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B472.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B867.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Flash
F0
284B162.6 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B472.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B205.9 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B205.9 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek LLM 67B
F0
67B50.0 GB2 tok/s4K ctx
dense
👁 Meta
Llama 4 Scout 17B 16E
F0
109B72.7 GB2 tok/s4K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B250.2 GB2 tok/s4K ctx
moe
👁 Cohere
Command R+ 104B
F0
104B70.2 GB2 tok/s4K ctx
dense
👁 Cohere
Command A 111B
F0
111B74.9 GB2 tok/s4K ctx
dense
👁 Mistral AI
Pixtral Large 124B
F0
124B84.3 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 VL 72B
F0
72B52.1 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
F0
72B52.1 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 70B
F0
70B50.9 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.1 405B
F0
405B258.0 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
F0
70B50.9 GB2 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 120B
F0
117B79.6 GB2 tok/s4K ctx
dense
👁 Google
Gemma 4 31B
F0
30.7B36.7 GB5 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B413.1 GB2 tok/s4K ctx
moe
MiniMax M2.7
F0
230B147.4 GB2 tok/s4K ctx
moe
Solar Open 100B
F0
100B76.0 GB2 tok/s4K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
F0
48B38.2 GB3 tok/s4K ctx
dense
K EXAONE 236B A23B
F0
236B174.9 GB2 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F0
70B54.2 GB2 tok/s4K ctx
dense
Baichuan M3 235B
F0
235B174.2 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0
235B174.2 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F0
72B55.7 GB2 tok/s4K ctx
dense
Solar Open 100B i1
F0
100B76.0 GB2 tok/s4K ctx
dense
Solar Open 69B REAP i1
F0
69B53.5 GB2 tok/s4K ctx
dense
Hermes 4.3 36B
F0
36B29.5 GB8 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F0
70B54.2 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
F0
122B77.4 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 397B A17B
F0
397B292.0 GB2 tok/s4K ctx
dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

RTX 3090 24GB

24 GB VRAM

View tier list

RTX 3090 Ti 24GB

24 GB VRAM

View tier list

RTX 4090 24GB

24 GB VRAM

View tier list

RTX PRO 4000 Blackwell 24GB

24 GB VRAM

View tier list
Full RTX 4500 Ada 24GB pageCompare this hardware