Back to leaderboard

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

Global Score
79 vs 72
Hardware Fit
57 vs 71
Quality Score
89 vs 72

Hardware

qwen3.5:27b gemma4:e2b
MachineAZW GTR ProDell Inc. Inspiron 15 3530
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SIntel Gen Intel® Core™ i7-1355U
Cores3212
RAM125 GB31 GB
GPUIntegrated / Apple SiliconRaptor Lake-P [Iris Xe Graphics]
OSUbuntu 24.04.4 LTScachyos rolling
Archx64x64
Power Modeperformancelow-power

Performance

qwen3.5:27b gemma4:e2b
Tokens/sec10.710.8
First chunk341 ms1408 ms
TTFT341 ms1.4 s
Load time10.2 s6.0 s
Memory usage39.7 GB7.2 GB
Memory %32%23%

HW Fit Score Breakdown

qwen3.5:27b

Speed
9/50
TTFT
20/20
Memory
28/30

gemma4:e2b

Speed
21/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5:27b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma4:e2b

Reasoning
10/20
Coding
16/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:27b details | View gemma4:e2b 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