Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
llama-3.1-8b-instruct
LM-STUDIO GGUFllama · 8B · Q8_0
Apr 26, 2026 · AMD Ryzen 5 5500
Global Score
85 vs 81
Hardware Fit
83 vs 100
Quality Score
86 vs 73
Hardware
Kimi-48B:48B llama-3.1-8b-instr…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCASUS
CPUIntel Core™ i7-14700FAMD Ryzen 5 5500
Cores2812
RAM64 GB31 GB
GPUNVIDIA GeForce RTX 5080Navi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Enterprise 10.0.26200Nobara Linux 43
Archx64x64
Power Modebalancedperformance
Performance
Kimi-48B:48B llama-3.1-8b-instr…
Tokens/sec32.835.6
First chunk724 ms52 ms
TTFT724 ms256 ms
Load time20.9 sN/A
Memory usage25.8 GB8.6 GB
Memory %41%28%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
llama-3.1-8b-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
Kimi-48B:48B
Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama-3.1-8b-instruct
Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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