starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Jun 26, 2026 · Cortex-A78AE
glm-4.7-flash:q4_K_M
OLLAMA GGUFglm4moelite · 29.9B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
Global Score
35 vs 81
Hardware Fit
100 vs 89
Quality Score
7 vs 77
Hardware
starcoder2:3b glm-4.7-flash:q4_K_M
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUS
CPUCortex-A78AEIntel Core™ i5-14600KF
Cores620
RAM7 GB32 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 4070 Ti SUPER
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
starcoder2:3b glm-4.7-flash:q4_K_M
Tokens/sec31.535.1
First chunk392 ms440 ms
TTFT392 ms440 ms
Load time4.8 s11.6 s
Memory usage1.8 GB18.4 GB
Memory %24%58%
HW Fit Score Breakdown
starcoder2:3b
Speed
50/50
TTFT
20/20
Memory
30/30
glm-4.7-flash:q4_K_M
Speed
49/50
TTFT
20/20
Memory
20/30
Quality
starcoder2:3b
Reasoning
0/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
glm-4.7-flash:q4_K_M
Reasoning
13/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
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