Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
qwen/qwen3-30b-a3b-2507
LM-STUDIO GGUFqwen3moe · 30B · Q3_K_L
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
85 vs 88
Hardware Fit
83 vs 87
Quality Score
86 vs 89
Hardware
Kimi-48B:48B qwen/qwen3-30b-a3b…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCASUS
CPUIntel Core™ i7-14700FAMD Ryzen 7 7800X3D 8-Core Processor
Cores2816
RAM64 GB31 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 Enterprise 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedperformance
Performance
Kimi-48B:48B qwen/qwen3-30b-a3b…
Tokens/sec32.8122.8
First chunk724 ms10 ms
TTFT724 ms153 ms
Load time20.9 sN/A
Memory usage25.8 GB20.1 GB
Memory %41%66%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
qwen/qwen3-30b-a3b-2507
Speed
50/50
TTFT
20/20
Memory
17/30
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
qwen/qwen3-30b-a3b-2507
Reasoning
18/20
Coding
19/20
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