Back to leaderboard

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Good

Mar 5, 2026 · Apple M1 Max

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score
62 vs 66
Hardware Fit
100 vs 40
Quality Score
46 vs 77

Hardware

qwen3.5:0.8b gemma4:31b
MachineMacBook ProASUSTeK COMPUTER INC. GX10
CPUApple M1 MaxCortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M1 MaxDevice 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.5:0.8b gemma4:31b
Tokens/sec65.810.7
First chunk230 ms983 ms
TTFT230 ms20.3 s
Load time1.5 s8.8 s
Memory usage2.6 GB21.4 GB
Memory %8%18%

HW Fit Score Breakdown

qwen3.5:0.8b

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

gemma4:31b

Speed
10/50
TTFT
0/20
Memory
30/30

Quality

qwen3.5:0.8b

Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

gemma4:31b

Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:0.8b 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