qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Global Score
79 vs 73
Hardware Fit
59 vs 93
Quality Score
87 vs 65
Hardware
qwen3.6-35b-a3b lfm2.5:latest
MachineDocker ContainerLENOVO 20L7CTO1WW
CPUIntel Gen Intel® Core™ i9-11900HIntel Core™ i5-8350U
Cores168
RAM15 GB23 GB
GPUTigerLake-H GT1 [UHD Graphics]Kaby Lake-R GT2 [UHD Graphics 620]
OSUbuntu 26.04 LTSFedora Linux 44
Archx64x64
Power Modeperformanceperformance
Performance
qwen3.6-35b-a3b lfm2.5:latest
Tokens/sec9.318.3
First chunk21 ms981 ms
TTFT3.6 s981 ms
Load time32.0 s8.0 s
Memory usage1.8 GB4.9 GB
Memory %12%21%
HW Fit Score Breakdown
qwen3.6-35b-a3b
Speed
17/50
TTFT
12/20
Memory
30/30
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
Quality
qwen3.6-35b-a3b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate 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