deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
Global Score
37 vs 89
Hardware Fit
73 vs 97
Quality Score
22 vs 86
Hardware
deepseek-r1:1.5b qwen/qwen3.6-35b-a3b
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M5 Max
Cores818
RAM23 GB64 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M5 Max
OSFedora Linux 43macOS 27.0
Archx64arm64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b qwen/qwen3.6-35b-a3b
Tokens/sec18.4130.2
First chunk593 ms5 ms
TTFT30.0 s135 ms
Load time3.8 sN/A
Memory usage1.0 GB26.6 GB
Memory %4%42%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
deepseek-r1:1.5b
Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Weak
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