Back to leaderboard

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
77 vs 81
Hardware Fit
53 vs 100
Quality Score
87 vs 73

Hardware

qwen3.5:35b gemma3n:latest
MachineASUSSupermicro AS -2015HS-TNR
CPUIntel Core™ i5-14600KFAMD EPYC 9654P 96-Core Processor
Cores2064
RAM32 GB128 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSMicrosoft Windows 11 Famille 10.0.26200Ubuntu 24.04.3 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3.5:35b gemma3n:latest
Tokens/sec16.0108.7
First chunk719 ms333 ms
TTFT719 ms333 ms
Load time17.8 s4.5 s
Memory usage25.0 GB8.6 GB
Memory %79%7%

HW Fit Score Breakdown

qwen3.5:35b

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

gemma3n:latest

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

Quality

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

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

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