Back to leaderboard

gemma4:latest

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Jun 5, 2026 · AMD Ryzen 7 5800H

qwen3.5:122b-a10b

OLLAMA GGUF

qwen35moe · 125.1B · Q4_K_M

Excellent

Mar 12, 2026 · AMD RYZEN AI MAX+ 395

Global Score
89 vs 80
Hardware Fit
83 vs 52
Quality Score
92 vs 92

Hardware

gemma4:latest qwen3.5:122b-a10b
MachineLENOVO 82JQAZW GTR Pro
CPUAMD Ryzen 7 5800HAMD RYZEN AI MAX+ 395
Cores1632
RAM16 GB125 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPURadeon 8060S
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance

Performance

gemma4:latest qwen3.5:122b-a10b
Tokens/sec46.319.1
First chunk824 ms467 ms
TTFT3.8 s467 ms
Load time21.0 s30.0 s
Memory usage8.9 GB89.3 GB
Memory %56%72%

HW Fit Score Breakdown

gemma4:latest

Speed
50/50
TTFT
11/20
Memory
22/30

qwen3.5:122b-a10b

Speed
18/50
TTFT
20/20
Memory
14/30

Quality

gemma4:latest

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:122b-a10b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma4:latest details | View qwen3.5:122b-a10b 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