Back to leaderboard

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_S

Not Rec.

Apr 20, 2026 · Apple M2 Max

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
82 vs 94
Hardware Fit
80 vs 97
Quality Score
83 vs 93

Hardware

qwen3.6-35b-a3b gpt-oss:20b
MachineMac StudioGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M2 MaxIntel Core™ i5-14400F
Cores1216
RAM96 GB32 GB
GPUApple M2 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.1Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.6-35b-a3b gpt-oss:20b
Tokens/sec54.780.4
First chunk32 ms139 ms
TTFT30.0 s1.6 s
Load timeN/A11.6 s
Memory usage30.3 GB11.9 GB
Memory %32%37%

HW Fit Score Breakdown

qwen3.6-35b-a3b

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

gpt-oss:20b

Speed
50/50
TTFT
19/20
Memory
28/30

Quality

qwen3.6-35b-a3b

Reasoning
18/20
Coding
10/20
Instruction
18/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gpt-oss:20b

Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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