deepseek-r1:latest
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
23 vs 68
Hardware Fit
70 vs 59
Quality Score
3 vs 72
Hardware
deepseek-r1:latest qwen2.5-coder:7b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUS
CPUCortex-A78AEIntel Gen Intel® Core™ i7-13700K
Cores624
RAM7 GB64 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3070
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
deepseek-r1:latest qwen2.5-coder:7b
Tokens/sec9.834.4
First chunk1206 ms1991 ms
TTFT1.2 s2.0 s
Load time17.8 s40.6 s
Memory usage4.8 GB5.0 GB
Memory %65%8%
HW Fit Score Breakdown
deepseek-r1:latest
Speed
32/50
TTFT
20/20
Memory
18/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
deepseek-r1:latest
Reasoning
0/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
2/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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