Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
qwen3-vl:8b
OLLAMA GGUFqwen3vl · 8.8B · Q4_K_M
Apr 28, 2026 · Intel Xeon® Gold 6230
Global Score
86 vs 72
Hardware Fit
78 vs 89
Quality Score
89 vs 64
Hardware
Kimi-48B:48B qwen3-vl:8b
MachineGMKtec NucBox EVO-T2SHP HP Z8 G4 Workstation
CPUIntel Core™ Ultra X7 358HIntel Xeon® Gold 6230
Cores1680
RAM64 GB252 GB
GPUIntel(R) Arc(TM) B390 GPUTU104GL [Quadro RTX 5000]
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
Kimi-48B:48B qwen3-vl:8b
Tokens/sec23.168.2
First chunk752 ms285 ms
TTFT752 ms2.0 s
Load time22.2 s42.4 s
Memory usage25.5 GB7.1 GB
Memory %40%3%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
qwen3-vl:8b
Speed
50/50
TTFT
9/20
Memory
30/30
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
qwen3-vl:8b
Reasoning
16/20
Coding
3/20
Instruction
10/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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