Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

Global Score
88 vs 76
Hardware Fit
90 vs 46
Quality Score
87 vs 89

Hardware

qwen/qwen3.6-35b-a3b gemma4:31b
MachineGMKtec EVO-X3MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M4 Max
Cores3216
RAM120 GB64 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4 Max
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.3.1
Archx64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.6-35b-a3b gemma4:31b
Tokens/sec49.022.4
First chunk44 ms565 ms
TTFT334 ms30.0 s
Load time61.3 s6.9 s
Memory usage59.8 GB43.9 GB
Memory %50%69%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
45/50
TTFT
20/20
Memory
25/30

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

Quality

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
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

gemma4:31b

Reasoning
16/20
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 qwen/qwen3.6-35b-a3b 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