Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
glm-4.7-flash:bf16
OLLAMA GGUFdeepseek2 · 29.9B · F16
Jun 26, 2026 · Cortex-X925
Global Score
86 vs 76
Hardware Fit
78 vs 73
Quality Score
89 vs 77
Hardware
Kimi-48B:48B glm-4.7-flash:bf16
MachineGMKtec NucBox EVO-T2SNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ Ultra X7 358HCortex-X925
Cores1620
RAM64 GB122 GB
GPUIntel(R) Arc(TM) B390 GPUDevice 2e12
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
Kimi-48B:48B glm-4.7-flash:bf16
Tokens/sec22.825.8
First chunk721 ms605 ms
TTFT721 ms605 ms
Load time23.0 s44.2 s
Memory usage25.5 GB57.0 GB
Memory %40%47%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
glm-4.7-flash:bf16
Speed
27/50
TTFT
20/20
Memory
26/30
Quality
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
glm-4.7-flash:bf16
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