lmstudio-community/gemma-4-e4b-it
LM-STUDIO GGUFgemma4 · Q4_K_M
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Sep 29, 2026 · Apple M5 Max
Global Score
76 vs 83
Hardware Fit
67 vs 80
Quality Score
80 vs 84
Hardware
lmstudio-community… openai/gpt-oss-20b
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M5 Max
Cores1618
RAM15 GB128 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M5 Max
OSUbuntu 26.04 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced
Performance
lmstudio-community… openai/gpt-oss-20b
Tokens/sec10.8138.4
First chunk44 ms3 ms
TTFT2.0 s30.0 s
Load time10.9 s6.8 s
Memory usage0.0 GB0.5 GB
Memory %0%0%
HW Fit Score Breakdown
lmstudio-community/gemm…
Speed
20/50
TTFT
17/20
Memory
30/30
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
lmstudio-community/gemm…
Reasoning
14/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
openai/gpt-oss-20b
Reasoning
18/20
Coding
12/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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