Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
64 vs 78
Hardware Fit
69 vs 47
Quality Score
62 vs 92

Hardware

qwen3.5:4b gemma4:31b
MachineLENOVO 20U30029MBAZW GTR Pro
CPUIntel Core™ i5-10210UAMD RYZEN AI MAX+ 395
Cores832
RAM15 GB125 GB
GPUCometLake-U GT2 [UHD Graphics]Radeon 8060S
OSPop 24.04 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modeperformanceperformance

Performance

qwen3.5:4b gemma4:31b
Tokens/sec7.49.8
First chunk1815 ms873 ms
TTFT1.8 s873 ms
Load time10.9 s7.0 s
Memory usage3.5 GB68.3 GB
Memory %23%55%

HW Fit Score Breakdown

qwen3.5:4b

Speed
19/50
TTFT
20/20
Memory
30/30

gemma4:31b

Speed
8/50
TTFT
16/20
Memory
23/30

Quality

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b details | View gemma4:31b 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