Back to leaderboard

qwen3.5:122b-a10b

OLLAMA GGUF

qwen35moe · 125.1B · Q4_K_M

Excellent

Mar 12, 2026 · AMD RYZEN AI MAX+ 395

gemma4:e2b-mlx

OLLAMA GGUF
Excellent

Aug 25, 2026 · Apple M1 Pro

Global Score
80 vs 82
Hardware Fit
52 vs 99
Quality Score
92 vs 75

Hardware

qwen3.5:122b-a10b gemma4:e2b-mlx
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPURadeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.5:122b-a10b gemma4:e2b-mlx
Tokens/sec19.170.4
First chunk467 ms96 ms
TTFT467 ms96 ms
Load time30.0 s2.5 s
Memory usage89.3 GB5.7 GB
Memory %72%36%

HW Fit Score Breakdown

qwen3.5:122b-a10b

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

gemma4:e2b-mlx

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

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

gemma4:e2b-mlx

Reasoning
14/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:122b-a10b details | View gemma4:e2b-mlx 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