gemma3:1b
OLLAMA GGUFgemma3 · 999.89M · Q4_K_M
Feb 28, 2026 · Apple M4
qwen/qwen3.6-35b-a3b:2
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
68 vs 73
Hardware Fit
98 vs 50
Quality Score
55 vs 83
Hardware
gemma3:1b qwen/qwen3.6-35b-a…
MachineMacBook AirSystem manufacturer
CPUApple M4AMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM32 GB31 GB
GPUApple M4Navi 44 [Radeon RX 9060 XT]
OSmacOS 26.3Ubuntu 26.04.1 LTS
Archarm64x64
Power Modeunknownlow-power
Performance
gemma3:1b qwen/qwen3.6-35b-a…
Tokens/sec39.410.5
First chunkN/A4 ms
TTFT362 ms1.7 s
Load time0.3 sN/A
Memory usage1.3 GB21.4 GB
Memory %4%69%
HW Fit Score Breakdown
gemma3:1b
Speed
40/50
TTFT
30/20
Memory
28/30
qwen/qwen3.6-35b-a3b:2
Speed
16/50
TTFT
18/20
Memory
16/30
Quality
gemma3:1b
Reasoning
6/20
Coding
13/20
Instruction
15/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
qwen/qwen3.6-35b-a3b:2
Reasoning
16/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
12/15
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest