VOOZH about

URL: https://willitrunai.com/my-results/gtx-1650-4gb

⇱ GTX 1650 4GB AI Tier List: 65 models ranked | WillItRunAI


AI Compatibility Tier List

GTX 1650 4GB

374 AI models ranked by how well they run on your 4 GB VRAM hardware. Best match: BGE M3 (score: 82).

374

Models tested

65

Can run

4 GB

VRAM

8

Best tok/s

Tier Distribution

A 7
B 9
C 49
F 309
A: 7B: 9C: 49F: 309
A

A Tier -- Great Fit (7 models)

Excellent performance with comfortable memory margins.

👁 BAAI
BGE M3
A82
0.57B3.6 GB8 tok/s8K ctx
dense
👁 Mixedbread AI
mxbai Embed Large
A79
0.34B3.5 GB5 tok/s1K ctx
dense
👁 Snowflake
Snowflake Arctic Embed L
A78
0.34B3.5 GB5 tok/s1K ctx
dense
👁 BAAI
BGE Large EN v1.5
A76
0.34B3.5 GB5 tok/s1K ctx
dense
👁 Nomic AI
Nomic Embed Text v1.5
A74
0.14B2.1 GB2 tok/s8K ctx
dense
👁 Mistral
Ministral 3 3B
A73
3B3.9 GB38 tok/s19K ctx
multimodal
👁 Jina AI
Jina Embeddings v3
A73
0.57B4.4 GB8 tok/s8K ctx
dense
B

B Tier -- Good Fit (9 models)

Solid performance, may need quantization or reduced context.

👁 Alibaba
Qwen 2.5 Coder 1.5B
B70
1.5B2.6 GB21 tok/s33K ctx
dense
👁 Alibaba
Qwen 3 1.7B
B69
1.7B4.0 GB24 tok/s16K ctx
dense
B66
0.02B1.6 GB2 tok/s0K ctx
dense
👁 Alibaba
Qwen 3.5 2B
B62
2B4.2 GB28 tok/s14K ctx
dense
👁 DeepSeek
DeepSeek R1 1.5B
B62
1.5B2.6 GB21 tok/s33K ctx
dense
👁 TinyLlama
TinyLlama 1.1B
B60
1.1B2.3 GB15 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 1.5B
B59
1.5B2.6 GB21 tok/s67K ctx
dense
👁 IBM
Granite 4.1 3B
B56
3B4.4 GB23 tok/s11K ctx
dense
👁 Google
Gemma 3 1B
B56
1B2.3 GB14 tok/s33K ctx
dense
C

C Tier -- Tight Fit (49 models)

Runs with offloading or significant compromises.

👁 Google
Gemma 2 2B
C55
2B4.1 GB28 tok/s8K ctx
dense
👁 Alibaba
Qwen 3 0.6B
C54
0.6B2.5 GB8 tok/s33K ctx
dense
EXAONE 3.5 2.4B Instruct
C53
2.4B3.0 GB34 tok/s70K ctx
dense
👁 Google
gemma 2b
C53
2B2.8 GB28 tok/s101K ctx
dense
gemma 2 2b it
C53
2B3.2 GB28 tok/s72K ctx
dense
👁 Meta
Llama 3.2 1B
C53
1B2.4 GB14 tok/s68K ctx
dense
Gemmasutra Mini 2B v1
C53
2B2.8 GB28 tok/s101K ctx
dense
gemma 2 2b it
C53
2B2.8 GB28 tok/s101K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 0.5B
C52
0.5B1.8 GB7 tok/s131K ctx
dense
👁 Alibaba
Qwen 3.5 0.6B
C52
0.6B2.5 GB8 tok/s44K ctx
dense
👁 Qwen
Qwen2.5 3B Instruct
C51
3B3.5 GB35 tok/s40K ctx
dense
Llama 3.2 3B Instruct
C51
3B3.5 GB35 tok/s40K ctx
dense
Ministral 3 3B Instruct 2512
C51
3B3.5 GB35 tok/s40K ctx
dense
HELVETE 3B
C51
3B3.5 GB35 tok/s40K ctx
dense
Llama 3.2 3B Instruct
C51
3B3.8 GB30 tok/s25K ctx
dense
Hermes 3 Llama 3.2 3B
C51
3B3.5 GB35 tok/s40K ctx
dense
stablelm zephyr 3b
C51
3B3.5 GB35 tok/s40K ctx
dense
StarCoder2 3B
C51
3B3.5 GB35 tok/s40K ctx
dense
AI21 Jamba Reasoning 3B
C50
3B3.5 GB35 tok/s40K ctx
dense
stablelm 3b 4e1t
C50
3B3.5 GB35 tok/s40K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C50
3B3.5 GB35 tok/s40K ctx
dense
stablelm 2 zephyr 1.6b
C50
1.6B2.5 GB22 tok/s147K ctx
dense
ai21labs AI21 Jamba2 3B
C50
3B3.5 GB35 tok/s40K ctx
dense
logos16v2 stablelm2 1.6b i1
C50
1.6B2.5 GB22 tok/s147K ctx
dense
HelpingAI 3B hindi i1
C50
3B3.5 GB35 tok/s40K ctx
dense
👁 Qwen
Qwen2.5 1.5B Instruct
C50
1.5B2.4 GB21 tok/s162K ctx
dense
AI21 Jamba2 3B
C50
3B3.5 GB35 tok/s40K ctx
dense
HelpingAI 3B hindi
C50
3B3.5 GB35 tok/s40K ctx
dense
AI21 Jamba2 3B i1
C50
3B3.5 GB35 tok/s40K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 1.5B
C50
1.5B2.4 GB21 tok/s162K ctx
dense
Yi Coder 1.5B Chat
C50
1.5B2.4 GB21 tok/s162K ctx
dense
Yi Coder 1.5B
C50
1.5B2.4 GB21 tok/s162K ctx
dense
👁 Unsloth
Falcon H1 1.5B Instruct
C50
1.5B2.4 GB21 tok/s162K ctx
dense
👁 BigCode
StarCoder2 3B
C50
3B3.6 GB38 tok/s16K ctx
dense
👁 Unsloth
Qwen3.5 4B
C49
4B4.2 GB17 tok/s9K ctx
dense
gemma 3 4b it
C49
4B4.2 GB17 tok/s9K ctx
dense
gemma 3 4b it
C49
4B4.2 GB17 tok/s9K ctx
dense
EXAONE 4.0 1.2B
C48
1.2B2.2 GB17 tok/s224K ctx
dense
Llama 3.2 1B Instruct Q8 0
C48
1B2.2 GB14 tok/s257K ctx
dense
TinyLlama 1.1B Chat v1.0
C48
1.1B2.1 GB15 tok/s252K ctx
dense
TinyLlama 1.1B Chat v0.3
C47
1.1B2.1 GB15 tok/s252K ctx
dense
👁 TinyLlama
TinyLlama 1.1B Chat v0.6
C47
1.1B2.1 GB15 tok/s252K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
C47
1.1B2.1 GB15 tok/s252K ctx
dense
Llama 3.2 1B Instruct
C47
1B2.0 GB14 tok/s285K ctx
dense
gemma 3 1b it
C47
1B2.0 GB14 tok/s285K ctx
dense
Falcon3 1B Instruct abliterated
C46
1B2.0 GB14 tok/s285K ctx
dense
👁 Alibaba
Qwen 2.5 0.5B
C46
0.5B1.8 GB7 tok/s131K ctx
dense
SmolVLM 500M Instruct
C44
0.5B1.8 GB7 tok/s366K ctx
dense
embeddinggemma 300M
C41
0.3B1.6 GB4 tok/s393K ctx
dense
F

F Tier -- Can't Run (309 models)

Too heavy for this hardware.

granite embedding 107m multilingual
D38
0.11B1.5 GB2 tok/s422K ctx
dense
Falcon H1 Tiny 90M Instruct
D38
0.09B1.5 GB2 tok/s423K ctx
dense
👁 Meta
Llama 3.2 3B
F0
3B4.8 GB18 tok/s8K ctx
dense
👁 Meta
Llama 3.1 8B
F0
8B8.1 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.1 70B
F0
70B48.9 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.3 70B
F0
70B48.9 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.2 11B Vision
F0
11B10.0 GB2 tok/s4K ctx
vision
👁 Alibaba
Qwen 2.5 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 14B
F0
14B12.8 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 32B
F0
32B24.7 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 72B
F0
72B50.1 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 14B
F0
14B12.8 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 32B
F0
32B24.7 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 8B
F0
8B8.4 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 14B
F0
14B12.3 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 32B
F0
32B24.7 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 4B
F0
4B5.9 GB9 tok/s4K ctx
dense
👁 Alibaba
Qwen 3 235B A22B
F0
235B147.5 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3 30B A3B
F0
30.5B21.4 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 30B A3B Instruct
F0
30.5B21.4 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder-Next
F0
80B51.6 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-Coder 480B A35B Instruct
F0
480B297.0 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen3-VL 30B A3B Instruct
F0
30B21.1 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 4B
F0
4B5.9 GB9 tok/s4K ctx
dense
👁 Alibaba
Qwen 3.5 9B
F0
9B9.0 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3.5 27B
F0
27B20.9 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 3.5 35B A3B
F0
35B24.1 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.6 35B A3B
F0
35B26.8 GB2 tok/s4K ctx
+1moe
👁 Alibaba
Qwen 3.6 27B
F0
27B18.7 GB2 tok/s4K ctx
+1dense
👁 Alibaba
Qwen 3.5 122B A10B
F0
122B78.2 GB2 tok/s4K ctx
moe
👁 Alibaba
Qwen 3.5 397B A17B
F0
397B246.3 GB2 tok/s4K ctx
moe
👁 Google
Gemma 2 9B
F0
9B11.9 GB2 tok/s4K ctx
dense
👁 Google
Gemma 2 27B
F0
27B29.0 GB2 tok/s4K ctx
dense
👁 Google
Gemma 3 4B
F0
4B5.8 GB7 tok/s4K ctx
dense
👁 Google
Gemma 3 12B
F0
12B13.5 GB2 tok/s4K ctx
dense
👁 Google
Gemma 3 27B
F0
27B29.0 GB2 tok/s4K ctx
dense
👁 Mistral
Ministral 8B
F0
8B8.4 GB2 tok/s4K ctx
dense
👁 Mistral
Ministral 3 8B
F0
8B8.4 GB2 tok/s4K ctx
multimodal
👁 Mistral
Ministral 3 14B
F0
14B12.3 GB2 tok/s4K ctx
multimodal
👁 Mistral
Mistral Nemo 12B
F0
12B11.1 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 24B
F0
24B18.4 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 3.2 24B
F0
24B18.4 GB2 tok/s4K ctx
vision
👁 Mistral
Mistral 7B Instruct v0.3
F0
7B7.5 GB3 tok/s4K ctx
dense
👁 Mistral
Mixtral 8x7B
F0
47B31.9 GB2 tok/s4K ctx
moe
👁 Mistral
Mixtral 8x22B
F0
141B90.7 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 Distill 8B
F0
8B8.1 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 14B
F0
14B12.8 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 32B
F0
32B24.7 GB2 tok/s4K ctx
dense
👁 Microsoft
Phi 3.5 Mini 4B
F0
4B9.6 GB4 tok/s4K ctx
dense
👁 Microsoft
Phi 4 Mini 4B
F0
4B5.2 GB12 tok/s4K ctx
dense
F0
14B12.9 GB2 tok/s4K ctx
dense
👁 Microsoft
Phi-4-reasoning-plus 14B
F0
14.7B13.3 GB2 tok/s4K ctx
dense
👁 Zhipu
GLM-4 9B
F0
9B7.4 GB2 tok/s4K ctx
dense
👁 IBM
Granite 3.1 8B
F0
8B8.1 GB3 tok/s4K ctx
state-space
👁 IBM
Granite 4.1 8B
F0
8B8.6 GB2 tok/s4K ctx
dense
👁 IBM
Granite 4.1 30B
F0
30B23.5 GB2 tok/s4K ctx
dense
👁 AllenAI
OLMo 2 13B
F0
13B11.7 GB2 tok/s4K ctx
dense
👁 Cohere
Command R 35B
F0
35B25.1 GB2 tok/s4K ctx
dense
👁 TII
Falcon 7B Instruct
F0
7B5.7 GB6 tok/s4K ctx
dense
👁 TII
Falcon 40B Instruct
F0
40B31.9 GB2 tok/s4K ctx
dense
👁 WizardLM
WizardLM 13B
F0
13B21.4 GB2 tok/s4K ctx
dense
👁 BigCode
StarCoder 7B
F0
7B12.9 GB2 tok/s4K ctx
dense
👁 BigCode
StarCoder 15B
F0
15B26.7 GB2 tok/s4K ctx
dense
👁 Meta
CodeLlama 7B Instruct
F0
7B13.4 GB2 tok/s4K ctx
dense
👁 Meta
CodeLlama 13B Instruct
F0
13B21.4 GB2 tok/s4K ctx
dense
👁 BigCode
StarCoder2 7B
F0
7B6.1 GB5 tok/s4K ctx
dense
👁 BigCode
StarCoder2 15B
F0
15B13.3 GB2 tok/s4K ctx
dense
👁 MosaicML
MPT-7B-Instruct
F0
7B13.4 GB2 tok/s4K ctx
dense
👁 MosaicML
MPT-30B-Instruct
F0
30B46.3 GB2 tok/s4K ctx
dense
👁 InternLM
InternLM 7B
F0
7B13.4 GB2 tok/s4K ctx
dense
👁 InternLM
InternLM Chat 7B
F0
7B13.4 GB2 tok/s4K ctx
dense
👁 DevStral AI
DevStral 7B
F0
7B7.5 GB3 tok/s4K ctx
dense
👁 Mistral
Devstral Small 1.1
F0
24B18.4 GB2 tok/s4K ctx
dense
👁 Mistral
Devstral Small 2 24B Instruct
F0
24B18.4 GB2 tok/s4K ctx
dense
👁 Mistral
Devstral 2 123B Instruct
F0
123B81.7 GB2 tok/s4K ctx
dense
👁 Mistral
Mistral Small 4 119B
F0
119B79.3 GB2 tok/s4K ctx
moe
👁 Mistral
Leanstral 119B A6B
F0
119B82.7 GB2 tok/s4K ctx
moe
👁 Mistral
Mistral Large 3
F0
675B418.4 GB2 tok/s4K ctx
+1moe
👁 Mistral
Magistral Small 2507
F0
24B18.4 GB2 tok/s4K ctx
dense
👁 Mistral
Codestral 2 25.08
F0
22B17.2 GB2 tok/s4K ctx
dense
F0
744B474.2 GB2 tok/s4K ctx
moe
👁 Z.ai
GLM-5.1
F0
754B480.3 GB2 tok/s4K ctx
moe
F0
1000B618.7 GB2 tok/s4K ctx
moe
F0
1000B618.7 GB2 tok/s4K ctx
+1moe
👁 Moonshot AI
Kimi Linear 48B A3B
F0
48B31.5 GB2 tok/s4K ctx
linear
👁 Magistral AI
Magistral 7B
F0
7B7.5 GB3 tok/s4K ctx
dense
7B8.5 GB2 tok/s4K ctx
dense
👁 Nous Research
Nous Hermes 1.0
F0
9B19.0 GB2 tok/s4K ctx
dense
👁 Nous Research
Nous Dolphin 13B
F0
13B22.9 GB2 tok/s4K ctx
dense
👁 Baichuan
Baichuan 7B
F0
7B13.4 GB2 tok/s4K ctx
dense
👁 Baichuan
Baichuan 13B
F0
13B22.9 GB2 tok/s4K ctx
dense
👁 Cerebras
Cerebras-GPT 13B
F0
13B20.4 GB2 tok/s4K ctx
dense
👁 Stability AI
StableLM 2 12B
F0
12B22.1 GB2 tok/s4K ctx
dense
👁 Hugging Face H4
Zephyr 7B Beta
F0
7B7.5 GB3 tok/s4K ctx
dense
👁 OpenChat
OpenChat 7B
F0
7B7.5 GB3 tok/s4K ctx
dense
👁 Cohere
Aya Expanse 8B
F0
8B8.1 GB2 tok/s4K ctx
dense
👁 InternLM
InternLM 20B
F0
20B34.0 GB2 tok/s4K ctx
dense
👁 01.AI
Yi 34B Chat
F0
34B25.7 GB2 tok/s4K ctx
dense
8B8.1 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3 671B
F0
671B470.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V3.1 671B
F0
671B470.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Pro
F0
1600B865.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V4 Flash
F0
284B160.6 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek R1 671B
F0
671B470.2 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 16B
F0
16B14.4 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek Coder V2 236B
F0
236B203.9 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek V2.5 236B
F0
236B203.9 GB2 tok/s4K ctx
moe
👁 DeepSeek
DeepSeek LLM 7B
F0
7B12.9 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek LLM 67B
F0
67B48.0 GB2 tok/s4K ctx
dense
👁 Meta
Llama 4 Scout 17B 16E
F0
109B70.7 GB2 tok/s4K ctx
moe
👁 Meta
Llama 4 Maverick 17B 128E
F0
400B248.2 GB2 tok/s4K ctx
moe
👁 Cohere
Command R+ 104B
F0
104B68.2 GB2 tok/s4K ctx
dense
👁 Cohere
Command A 111B
F0
111B72.9 GB2 tok/s4K ctx
dense
👁 Microsoft
Phi 3 Mini 3.8B
F0
3.8B9.5 GB4 tok/s4K ctx
dense
👁 Microsoft
Phi 3 Medium 14B
F0
14B12.9 GB2 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 6B
F0
6B5.9 GB6 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 9B
F0
9B8.3 GB2 tok/s4K ctx
dense
👁 01.AI
Yi 1.5 34B
F0
34B25.7 GB2 tok/s4K ctx
dense
👁 01.AI
Yi Coder 9B
F0
9B8.3 GB2 tok/s4K ctx
dense
👁 Mistral AI
Codestral 22B
F0
22B17.2 GB2 tok/s4K ctx
dense
👁 Mistral AI
Codestral Mamba 7B
F0
7B6.1 GB5 tok/s4K ctx
state-space
👁 Mistral AI
Pixtral 12B
F0
12B11.1 GB2 tok/s4K ctx
dense
👁 Mistral AI
Pixtral Large 124B
F0
124B82.3 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 VL 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 VL 72B
F0
72B50.1 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 Math 72B
F0
72B50.1 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 70B
F0
70B48.9 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron Mini 4B
F0
4B5.7 GB10 tok/s4K ctx
dense
👁 LLaVA
LLaVA 1.5 7B
F0
7B13.4 GB2 tok/s4K ctx
dense
👁 LLaVA
LLaVA 1.6 13B
F0
13B21.4 GB2 tok/s4K ctx
dense
👁 OpenBMB
MiniCPM-V 2.6 8B
F0
8B8.1 GB2 tok/s2K ctx
dense
👁 InternLM
InternVL2 8B
F0
8B8.1 GB2 tok/s4K ctx
dense
F0
19B15.3 GB2 tok/s4K ctx
dense
👁 LMSYS
Vicuna 7B
F0
7B13.4 GB2 tok/s4K ctx
dense
👁 LMSYS
Vicuna 13B
F0
13B21.4 GB2 tok/s4K ctx
dense
👁 Teknium
OpenHermes 2.5 7B
F0
7B7.5 GB3 tok/s4K ctx
dense
👁 UC Berkeley
Starling LM 7B
F0
7B7.5 GB3 tok/s4K ctx
dense
👁 Intel
Neural Chat 7B
F0
7B7.5 GB3 tok/s4K ctx
dense
7B7.5 GB3 tok/s4K ctx
dense
👁 WizardLM
WizardMath 7B
F0
7B7.5 GB3 tok/s4K ctx
dense
👁 IBM
Granite Code 8B
F0
8B8.1 GB2 tok/s4K ctx
dense
👁 IBM
Granite Code 20B
F0
20B16.7 GB2 tok/s4K ctx
dense
👁 Tsinghua/Zhipu
CodeGeeX 4 9B
F0
9B7.4 GB2 tok/s4K ctx
dense
👁 Defog
SQLCoder 7B
F0
7B7.5 GB3 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 20B
F0
21B16.6 GB2 tok/s4K ctx
moe
F0
3B5.1 GB16 tok/s7K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 32B
F0
32B24.7 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron Nano 8B
F0
8B8.1 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron Nano 9B v2
F0
9B9.2 GB2 tok/s4K ctx
dense
👁 NVIDIA
Nemotron 3 Nano 30B
F0
30B22.0 GB2 tok/s4K ctx
dense
👁 LG AI
EXAONE 4.0 32B
F0
32B24.7 GB2 tok/s4K ctx
dense
F0
24B18.4 GB2 tok/s4K ctx
dense
👁 Meta
Llama 3.1 405B
F0
405B256.0 GB2 tok/s4K ctx
dense
👁 Alibaba
Qwen 2.5 3B
F0
3B5.3 GB14 tok/s6K ctx
dense
👁 Alibaba
Qwen 2.5 Coder 3B
F0
3B5.3 GB14 tok/s6K ctx
dense
👁 DeepSeek
DeepSeek R1 Distill 70B
F0
70B48.9 GB2 tok/s4K ctx
dense
👁 Allen AI
OLMo 2 7B
F0
7B7.5 GB3 tok/s4K ctx
dense
👁 IBM
Granite Code 3B
F0
3B5.6 GB12 tok/s6K ctx
dense
👁 IBM
Granite Code 34B
F0
34B25.7 GB2 tok/s4K ctx
dense
👁 OpenAI
GPT-OSS 120B
F0
117B77.6 GB2 tok/s4K ctx
dense
👁 Cohere
Aya Expanse 32B
F0
32B23.3 GB2 tok/s4K ctx
dense
👁 Mistral AI
Mistral Small 3.1 24B
F0
24B18.4 GB2 tok/s4K ctx
dense
👁 Microsoft
Phi-4 Mini Reasoning 4B
F0
3.8B5.1 GB13 tok/s4K ctx
dense
👁 Google
Gemma 4 E2B
F0
5.1B4.9 GB8 tok/s4K ctx
dense
👁 Google
Gemma 4 E4B
F0
8B7.5 GB2 tok/s4K ctx
dense
👁 Google
Gemma 4 26B A4B
F0
25.2B20.3 GB2 tok/s4K ctx
moe
👁 Google
Gemma 4 31B
F0
30.7B34.7 GB2 tok/s4K ctx
dense
👁 DeepSeek
DeepSeek V3.2
F0
671B411.1 GB2 tok/s4K ctx
moe
👁 NVIDIA
Nemotron Cascade 2 30B A3B
F0
30B22.5 GB2 tok/s4K ctx
moe
MiniMax M2.7
F0
230B145.4 GB2 tok/s4K ctx
moe
Solar Open 100B
F0
100B74.0 GB2 tok/s4K ctx
dense
Baichuan M2 32B Q4 K M
F0
32B24.6 GB2 tok/s4K ctx
dense
aya expanse 8b
F0
8B7.1 GB3 tok/s4K ctx
dense
baichuan inc Baichuan M2 32B
F0
32B24.6 GB2 tok/s4K ctx
dense
Codestral 22B v0.1
F0
22B17.3 GB2 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B18.8 GB2 tok/s4K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
F0
24B18.8 GB2 tok/s4K ctx
dense
DiscoPOP zephyr 7b gemma
F0
7B6.4 GB4 tok/s4K ctx
dense
dolphin 2.9.4 llama3.1 8b
F0
8B7.1 GB3 tok/s4K ctx
dense
Dolphin3.0 Llama3.1 8B
F0
8B7.1 GB3 tok/s4K ctx
dense
glm 4 9b chat 1m
F0
9B7.8 GB2 tok/s4K ctx
dense
HelpingAI2 9B
F0
9B7.8 GB2 tok/s4K ctx
dense
internlm JanusCoder 14B
F0
14B11.5 GB2 tok/s4K ctx
dense
internlm2 5 20b chat
F0
20B15.8 GB2 tok/s4K ctx
dense
Meta Llama 3.1 8B Instruct
F0
8B7.1 GB3 tok/s4K ctx
dense
NousResearch Hermes 4 14B
F0
14B11.5 GB2 tok/s4K ctx
dense
starcoder2 15b instruct v0.1
F0
15B12.2 GB2 tok/s4K ctx
dense
Yi 1.5 6B Chat
F0
6B5.7 GB6 tok/s4K ctx
dense
Yi 1.5 9B Chat
F0
9B7.8 GB2 tok/s4K ctx
dense
exaone 3.0 7.8b it
F0
7.8B7.0 GB3 tok/s4K ctx
dense
stablelm 2 1 6b chat imatrix
F0
6B5.7 GB6 tok/s4K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
F0
48B36.2 GB2 tok/s4K ctx
dense
Dolphin3.0 Llama3.1 8B
F0
8B7.1 GB3 tok/s4K ctx
dense
Mamba Codestral 7B v0.1
F0
7B6.4 GB5 tok/s4K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
F0
9B7.8 GB2 tok/s4K ctx
dense
HelpingAI2 6B
F0
6B5.7 GB6 tok/s4K ctx
dense
granite 8b code instruct 4k
F0
8B7.1 GB3 tok/s4K ctx
dense
internlm2 limarp chat 20b
F0
20B15.8 GB2 tok/s4K ctx
dense
Phi 4 reasoning vision 15B
F0
15B12.2 GB2 tok/s4K ctx
dense
Codestral 22B v0.1 IMat
F0
22B17.3 GB2 tok/s4K ctx
dense
internlm2 math plus 7b IMat
F0
7B6.4 GB4 tok/s4K ctx
dense
openchat 3.6 8b 20240522 IMat
F0
8B7.1 GB3 tok/s4K ctx
dense
EXAONE 3.5 7.8B Instruct
F0
7.8B7.0 GB3 tok/s4K ctx
dense
EXAONE 4.0 32B
F0
32B24.6 GB2 tok/s4K ctx
dense
K EXAONE 236B A23B
F0
236B172.9 GB2 tok/s4K ctx
dense
vntl llama3 8b v2
F0
8B7.1 GB3 tok/s4K ctx
dense
Codestral 22B v0.1
F0
22B17.3 GB2 tok/s4K ctx
dense
DeepSeek R1 0528 Qwen3 8B
F0
8B7.1 GB3 tok/s4K ctx
dense
EXAONE 3.5 7.8B Instruct
F0
7.8B7.0 GB3 tok/s4K ctx
dense
Qwen3.5 35B A3B
F0
35B26.8 GB2 tok/s4K ctx
dense
Qwen3.5 9B
F0
9B7.8 GB2 tok/s4K ctx
dense
starcoder2 15b instruct v0.1
F0
15B12.2 GB2 tok/s4K ctx
dense
DeepSeek R1 0528 Qwen3 8B
F0
8B7.1 GB3 tok/s4K ctx
dense
gemma 3 12b it
F0
12B10.0 GB2 tok/s4K ctx
dense
gemma 3 27b it
F0
27B20.9 GB2 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F0
70B52.2 GB2 tok/s4K ctx
dense
Llama 3 8B Instruct 32k v0.1
F0
8B7.1 GB3 tok/s4K ctx
dense
Meta Llama 3.1 8B Instruct
F0
8B7.1 GB3 tok/s4K ctx
dense
Meta Llama 3 8B Instruct
F0
8B7.1 GB3 tok/s4K ctx
dense
Mistral 7B Instruct v0.3
F0
7B6.4 GB4 tok/s4K ctx
dense
Mistral Small 24B Instruct 2501
F0
24B18.8 GB2 tok/s4K ctx
dense
mistral small 3.1 24b instruct 2503 hf
F0
24B18.8 GB2 tok/s4K ctx
dense
Yi 1.5 6B Chat
F0
6B5.7 GB6 tok/s4K ctx
dense
Yi Coder 9B Chat
F0
9B7.8 GB2 tok/s4K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
F0
7B6.4 GB4 tok/s4K ctx
dense
aya expanse 32b heretic MPOA i1
F0
32B24.6 GB2 tok/s4K ctx
dense
aya expanse 8b orthogonal heretic
F0
8B7.1 GB3 tok/s4K ctx
dense
aya expanse 8b orthogonal heretic i1
F0
8B7.1 GB3 tok/s4K ctx
dense
Baichuan M3 235B
F0
235B172.2 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0
235B172.2 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F0
72B53.7 GB2 tok/s4K ctx
dense
blossom v1 baichuan 7b i1
F0
7B6.4 GB4 tok/s4K ctx
dense
blossom v3 baichuan2 7b i1
F0
7B6.4 GB4 tok/s4K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
F0
7B6.4 GB4 tok/s4K ctx
dense
Codestral 21B Pruned i1
F0
21B16.6 GB2 tok/s4K ctx
dense
Codestral 22B v0.1 i1
F0
22B17.3 GB2 tok/s4K ctx
dense
Codestral RAG 19B Pruned i1
F0
19B15.1 GB2 tok/s4K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
F0
24B18.8 GB2 tok/s4K ctx
dense
dolphin v2 8b abliterated i1
F0
8B7.1 GB3 tok/s4K ctx
dense
EXAONE 3.5 7.8B Instruct i1
F0
7.8B7.0 GB3 tok/s4K ctx
dense
HelpingAI 15B i1
F0
15B12.2 GB2 tok/s4K ctx
dense
HelpingAI 9B 200k i1
F0
9B7.8 GB2 tok/s4K ctx
dense
HelpingAI 9B i1
F0
9B7.8 GB2 tok/s4K ctx
dense
HelpingAI2.5 10B i1
F0
10B8.6 GB2 tok/s4K ctx
dense
HelpingAI2.5 5B i1
F0
5B4.9 GB10 tok/s4K ctx
dense
HelpingAI2 6B i1
F0
6B5.7 GB6 tok/s4K ctx
dense
HelpingAI2 9B i1
F0
9B7.8 GB2 tok/s4K ctx
dense
Helply 10.2b chat i1
F0
10.2B8.7 GB2 tok/s4K ctx
dense
internlm2 5 1 8b chat i1
F0
8B7.1 GB3 tok/s4K ctx
dense
internlm2 5 7b chat i1
F0
7B6.4 GB4 tok/s4K ctx
dense
internlm2 math plus 20b i1
F0
20B15.8 GB2 tok/s4K ctx
dense
internlm3 8b instruct abliterated i1
F0
8B7.1 GB3 tok/s4K ctx
dense
MD Judge v0 2 internlm2 7b i1
F0
7B6.4 GB4 tok/s4K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
F0
7B6.4 GB4 tok/s4K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
F0
7B6.4 GB4 tok/s4K ctx
dense
SOLAR 10.7B v1.0
F0
10.7B9.1 GB2 tok/s4K ctx
dense
solar finalised finetuned Model 10.7B i1
F0
10.7B9.1 GB2 tok/s4K ctx
dense
Solar Open 100B i1
F0
100B74.0 GB2 tok/s4K ctx
dense
Solar Open 69B REAP i1
F0
69B51.5 GB2 tok/s4K ctx
dense
starcoder2 15b i1
F0
15B12.2 GB2 tok/s4K ctx
dense
Yi 9B Coder i1
F0
9B7.8 GB2 tok/s4K ctx
dense
zephyr 7b dpo full i1
F0
7B6.4 GB4 tok/s4K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
F0
7B6.4 GB4 tok/s4K ctx
dense
Hermes 2 Pro Llama 3 8B
F0
8B7.1 GB3 tok/s4K ctx
dense
Hermes 2 Pro Mistral 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
Hermes 3 Llama 3.1 8B
F0
8B7.1 GB3 tok/s4K ctx
dense
Hermes 4.3 36B
F0
36B27.5 GB2 tok/s4K ctx
dense
Nous Hermes 2 Mistral 7B DPO
F0
7B6.4 GB4 tok/s4K ctx
dense
starcoder2 7b
F0
7B6.4 GB4 tok/s4K ctx
dense
jointpreferences mistral 7b sft helpful
F0
7B6.4 GB4 tok/s4K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
F0
7B6.4 GB4 tok/s4K ctx
dense
stabilityai japanese stablelm base gamma 7b
F0
7B6.4 GB4 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F0
70B52.2 GB2 tok/s4K ctx
dense
Codestral 22B v0.1
F0
22B17.3 GB2 tok/s4K ctx
dense
Mistral 7B Instruct v0.3
F0
7B6.4 GB4 tok/s4K ctx
dense
StarCoder2 15B
F0
15B12.2 GB2 tok/s4K ctx
dense
StarCoder2 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
baichuan2 7b chat
F0
7B6.4 GB4 tok/s4K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
F0
14B11.5 GB2 tok/s4K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
F0
14B11.5 GB2 tok/s4K ctx
dense
stablelm 2 zephyr 1 6b
F0
6B5.7 GB6 tok/s4K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
F0
8B7.1 GB3 tok/s4K ctx
dense
japanese stablelm instruct gamma 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
Llama 2 7B Chat
F0
7B6.4 GB4 tok/s4K ctx
dense
Mistral 7B Instruct v0.2
F0
7B6.4 GB4 tok/s4K ctx
dense
Nous Hermes 2 SOLAR 10.7B
F0
10.7B9.1 GB2 tok/s4K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
F0
10.7B9.1 GB2 tok/s4K ctx
dense
zephyr 7B alpha
F0
7B6.4 GB4 tok/s4K ctx
dense
zephyr 7B beta
F0
7B6.4 GB4 tok/s4K ctx
dense
Falcon H1 7B Instruct
F0
7B6.4 GB4 tok/s4K ctx
dense
Falcon H1R 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
falcon mamba 7b instruct Q4 K M
F0
7B6.4 GB5 tok/s4K ctx
dense
👁 Unsloth
DeepSeek R1 0528 Qwen3 8B
F0
8B7.1 GB3 tok/s4K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Llama 8B
F0
8B7.1 GB3 tok/s4K ctx
dense
👁 Unsloth
DeepSeek R1 Distill Qwen 14B
F0
14B11.5 GB2 tok/s4K ctx
dense
👁 Unsloth
Falcon H1R 7B
F0
7B6.4 GB4 tok/s4K ctx
dense
👁 Unsloth
gemma 3 27b it
F0
27B20.9 GB2 tok/s4K ctx
dense
👁 Unsloth
Mistral Small 3.2 24B Instruct 2506
F0
24B18.8 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 122B A10B
F0
122B75.4 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 27B
F0
27B20.9 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 35B A3B
F0
35B26.8 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 397B A17B
F0
397B290.0 GB2 tok/s4K ctx
dense
👁 Unsloth
Qwen3.5 9B
F0
9B7.8 GB2 tok/s4K ctx
dense
speechless zephyr code functionary 7b
F0
7B6.4 GB4 tok/s4K ctx
dense
llava llama 3 8b v1 1
F0
8B7.1 GB3 tok/s4K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
F0
24B18.8 GB2 tok/s4K ctx
dense

Compare with...

See How Other Hardware Stacks Up

Check tier lists for similar GPUs and Apple Silicon configs

Intel Arc A370M 4GB

4 GB VRAM

View tier list

RTX 3050 Ti Laptop 4GB

4 GB VRAM

View tier list

RTX 2060 6GB

6 GB VRAM

View tier list

RTX 4050 Laptop 6GB

6 GB VRAM

View tier list
Full GTX 1650 4GB pageCompare this hardware