Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
89 vs 88
Hardware Fit
97 vs 77
Quality Score
86 vs 93

Hardware

qwen/qwen3.6-35b-a3b gemma-4-26b-a4b-it…
MachineMacBook ProASUS
CPUApple M5 MaxAMD Ryzen 7 7800X3D 8-Core Processor
Cores1816
RAM64 GB31 GB
GPUApple M5 MaxNVIDIA GeForce RTX 4090, Raphael
OSmacOS 27.0cachyos rolling
Archarm64x64
Power Modebalancedperformance

Performance

qwen/qwen3.6-35b-a3b gemma-4-26b-a4b-it…
Tokens/sec130.2169.2
First chunk5 ms5 ms
TTFT135 ms122 ms
Load timeN/AN/A
Memory usage26.6 GB26.0 GB
Memory %42%85%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
27/30

gemma-4-26b-a4b-it-qat

Speed
50/50
TTFT
20/20
Memory
7/30

Quality

qwen/qwen3.6-35b-a3b

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma-4-26b-a4b-it-qat

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View gemma-4-26b-a4b-it… 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