Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex-mtp
LM-STUDIO GGUFqwen35moe · 35B
Jun 19, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
85 vs 92
Hardware Fit
83 vs 87
Quality Score
86 vs 94
Hardware
Kimi-48B:48B qwen3.6-35b-a3b-cl…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i7-14700FAMD Ryzen 5 5600X 6-Core Processor
Cores2812
RAM64 GB47 GB
GPUNVIDIA GeForce RTX 5080AD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Enterprise 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
Kimi-48B:48B qwen3.6-35b-a3b-cl…
Tokens/sec32.842.6
First chunk724 ms13 ms
TTFT724 ms3.1 s
Load time20.9 sN/A
Memory usage25.8 GB23.2 GB
Memory %41%49%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
qwen3.6-35b-a3b-claude-…
Speed
50/50
TTFT
12/20
Memory
25/30
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
qwen3.6-35b-a3b-claude-…
Reasoning
20/20
Coding
16/20
Instruction
19/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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