gemma-2-2b-it
LM-STUDIO GGUFgemma2 · 2B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
Global Score
58 vs 89
Hardware Fit
50 vs 97
Quality Score
62 vs 86
Hardware
gemma-2-2b-it qwen/qwen3.6-35b-a3b
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M5 Max
Cores418
RAM16 GB64 GB
GPUIntel(R) HD Graphics 5500Apple M5 Max
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
gemma-2-2b-it qwen/qwen3.6-35b-a3b
Tokens/sec3.6130.2
First chunk4509 ms5 ms
TTFT4.5 s135 ms
Load timeN/AN/A
Memory usage1.6 GB26.6 GB
Memory %10%42%
HW Fit Score Breakdown
gemma-2-2b-it
Speed
14/50
TTFT
12/20
Memory
24/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
gemma-2-2b-it
Reasoning
11/20
Coding
8/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
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
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