qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
deepseek-r1:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
Global Score
70 vs 66
Hardware Fit
93 vs 63
Quality Score
60 vs 67
Hardware
qwen3.5-2b-mlx deepseek-r1:7b
MachineMacBook AirGigabyte Technology Co., Ltd. H170M-D3H
CPUApple M4Intel Core™ i5-6500
Cores104
RAM32 GB16 GB
GPUApple M4GP104 [GeForce GTX 1070]
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
qwen3.5-2b-mlx deepseek-r1:7b
Tokens/sec32.935.6
First chunk3096 ms224 ms
TTFT3.1 s7.5 s
Load timeN/A7.7 s
Memory usage2.5 GB4.6 GB
Memory %8%29%
HW Fit Score Breakdown
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
Memory
30/30
deepseek-r1:7b
Speed
50/50
TTFT
7/20
Memory
6/30
Quality
qwen3.5-2b-mlx
Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
deepseek-r1:7b
Reasoning
16/20
Coding
10/20
Instruction
9/20
Structured
10/15
Math
14/15
Multilingual
8/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Adequate 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