qwen36-distill-apex
OLLAMA GGUFJul 17, 2026 · Apple M5 Max
lmstudio-community/gemma-4-e4b-it
LM-STUDIO GGUFgemma4 · Q4_K_M
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
36 vs 76
Hardware Fit
100 vs 67
Quality Score
8 vs 80
Hardware
qwen36-distill-apex lmstudio-community…
MachineMacBook ProDocker Container
CPUApple M5 MaxIntel Gen Intel® Core™ i9-11900H
Cores1816
RAM64 GB15 GB
GPUApple M5 MaxTigerLake-H GT1 [UHD Graphics]
OSmacOS 27.0Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen36-distill-apex lmstudio-community…
Tokens/sec55.210.8
First chunk210 ms44 ms
TTFT210 ms2.0 s
Load time4.8 s10.9 s
Memory usage0.9 GB0.0 GB
Memory %2%0%
HW Fit Score Breakdown
qwen36-distill-apex
Speed
50/50
TTFT
20/20
Memory
30/30
lmstudio-community/gemm…
Speed
20/50
TTFT
17/20
Memory
30/30
Quality
qwen36-distill-apex
Reasoning
8/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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
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