Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
qwen3.8:27b-bf16
OLLAMA GGUFqwen35 · 27.3B · BF16
Aug 22, 2026 · AMD EPYC 7713 64-Core Processor
Global Score
86 vs 85
Hardware Fit
78 vs 77
Quality Score
89 vs 88
Hardware
Kimi-48B:48B qwen3.8:27b-bf16
MachineGMKtec NucBox EVO-T2SDell Inc. PowerEdge XE8545
CPUIntel Core™ Ultra X7 358HAMD EPYC 7713 64-Core Processor
Cores16128
RAM64 GB1007 GB
GPUIntel(R) Arc(TM) B390 GPUGA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]
OSMicrosoft Windows 11 Pro 10.0.26200Rocky Linux 8.10
Archx64x64
Power Modebalancedunknown
Performance
Kimi-48B:48B qwen3.8:27b-bf16
Tokens/sec22.827.2
First chunk721 ms237 ms
TTFT721 ms237 ms
Load time23.0 s43.8 s
Memory usage25.5 GB68.8 GB
Memory %40%7%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
qwen3.8:27b-bf16
Speed
27/50
TTFT
20/20
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
qwen3.8:27b-bf16
Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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