Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Nov 4, 2026 · Intel Core™ i7-9700

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
29 vs 77
Hardware Fit
84 vs 53
Quality Score
6 vs 87

Hardware

qwen3:4b qwen3.5:35b
MachineVMware, Inc. VMware Virtual PlatformASUS
CPUIntel Core™ i7-9700Intel Core™ i5-14600KF
Cores420
RAM16 GB32 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 4070 Ti SUPER
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modeunknownbalanced

Performance

qwen3:4b qwen3.5:35b
Tokens/sec10.416.0
First chunk857 ms719 ms
TTFT857 ms719 ms
Load time41.0 s17.8 s
Memory usage3.0 GB25.0 GB
Memory %19%79%

HW Fit Score Breakdown

qwen3:4b

Speed
34/50
TTFT
20/20
Memory
30/30

qwen3.5:35b

Speed
23/50
TTFT
20/20
Memory
10/30

Quality

qwen3:4b

Reasoning
0/20
Coding
2/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen3.5:35b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:4b details | View qwen3.5:35b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest