Back to leaderboard

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
85 vs 80
Hardware Fit
78 vs 60
Quality Score
88 vs 88

Hardware

Kimi-48B:48B qwen/qwen3.6-35b-a3b
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxSystem manufacturer
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorAMD Ryzen 7 5800X 8-Core Processor
Cores3216
RAM31 GB31 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUNavi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Home 10.0.26200Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedperformance

Performance

Kimi-48B:48B qwen/qwen3.6-35b-a3b
Tokens/sec43.015.0
First chunk700 ms49 ms
TTFT700 ms759 ms
Load time29.4 sN/A
Memory usage25.8 GB22.2 GB
Memory %83%71%

HW Fit Score Breakdown

Kimi-48B:48B

Speed
50/50
TTFT
20/20
Memory
8/30

qwen/qwen3.6-35b-a3b

Speed
25/50
TTFT
20/20
Memory
15/30

Quality

Kimi-48B:48B

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View Kimi-48B:48B details | View qwen/qwen3.6-35b-a3b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest