deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Mar 6, 2026 · Apple M4
parable-qwen3-4b-claude-fable-5
LM-STUDIO GGUFqwen3 · 4B · Q4_K_M
Oct 24, 2026 · Intel Core™ i3-9100F
Global Score
66 vs 67
Hardware Fit
100 vs 66
Quality Score
51 vs 67
Hardware
deepseek-r1:1.5b parable-qwen3-4b-c…
MachineMacBook AirGigabyte Technology Co., Ltd. H310M S2 2.0
CPUApple M4Intel Core™ i3-9100F
Cores104
RAM32 GB16 GB
GPUApple M4Virtual Desktop Monitor, NVIDIA GeForce GTX 1650
OSmacOS 26.3Майкрософт Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
deepseek-r1:1.5b parable-qwen3-4b-c…
Tokens/sec85.44.3
First chunk115 ms13 ms
TTFT115 ms1.9 s
Load time0.5 sN/A
Memory usage2.6 GB3.0 GB
Memory %8%19%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
50/50
TTFT
20/20
Memory
30/30
parable-qwen3-4b-claude…
Speed
16/50
TTFT
20/20
Memory
30/30
Quality
deepseek-r1:1.5b
Reasoning
14/20
Coding
4/20
Instruction
8/20
Structured
6/15
Math
14/15
Multilingual
5/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
parable-qwen3-4b-claude…
Reasoning
12/20
Coding
12/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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