qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
gemma-3-1b-it
LM-STUDIO GGUFgemma3 · 1B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
Global Score
68 vs 59
Hardware Fit
59 vs 76
Quality Score
72 vs 52
Hardware
qwen2.5-coder:7b gemma-3-1b-it
MachineASUSLENOVO 20BUS00700
CPUIntel Gen Intel® Core™ i7-13700KIntel Core™ i5-5300U
Cores244
RAM64 GB16 GB
GPUNVIDIA GeForce RTX 3070Intel(R) HD Graphics 5500
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modeunknownbalanced
Performance
qwen2.5-coder:7b gemma-3-1b-it
Tokens/sec34.48.7
First chunk1991 ms2078 ms
TTFT2.0 s2.1 s
Load time40.6 sN/A
Memory usage5.0 GB0.8 GB
Memory %8%5%
HW Fit Score Breakdown
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
gemma-3-1b-it
Speed
29/50
TTFT
19/20
Memory
28/30
Quality
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
gemma-3-1b-it
Reasoning
4/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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