gemma-4-e2b-it@q5_k_xl
LM-STUDIO GGUFgemma4 · Q5_K_XL
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
amd-olmo-1b-sft
LM-STUDIO GGUFolmo · 1B · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
Global Score
79 vs 44
Hardware Fit
81 vs 75
Quality Score
78 vs 30
Hardware
gemma-4-e2b-it@q5_… amd-olmo-1b-sft
MachineDocker ContainerLENOVO 20BUS00700
CPUIntel Gen Intel® Core™ i9-11900HIntel Core™ i5-5300U
Cores164
RAM15 GB16 GB
GPUTigerLake-H GT1 [UHD Graphics]Intel(R) HD Graphics 5500
OSUbuntu 26.04 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modeperformancebalanced
Performance
gemma-4-e2b-it@q5_… amd-olmo-1b-sft
Tokens/sec17.29.2
First chunk7 ms2093 ms
TTFT1.6 s2.1 s
Load time8.9 sN/A
Memory usage0.0 GB0.7 GB
Memory %0%4%
HW Fit Score Breakdown
gemma-4-e2b-it@q5_k_xl
Speed
32/50
TTFT
19/20
Memory
30/30
amd-olmo-1b-sft
Speed
30/50
TTFT
19/20
Memory
26/30
Quality
gemma-4-e2b-it@q5_k_xl
Reasoning
11/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
amd-olmo-1b-sft
Reasoning
4/20
Coding
2/20
Instruction
11/20
Structured
9/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Poor
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