Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

lfm2.5:latest

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Good

Jun 11, 2026 · Intel Core™ i5-8350U

Global Score
35 vs 73
Hardware Fit
45 vs 93
Quality Score
30 vs 65

Hardware

qwen3.5:35b-a3b-q4… lfm2.5:latest
MachineMicro-Star International Co., Ltd. MS-7D98LENOVO 20L7CTO1WW
CPUIntel Core™ i9-14900KIntel Core™ i5-8350U
Cores328
RAM128 GB23 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Kaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 Pro 10.0.26200Fedora Linux 44
Archx64x64
Power Modebalancedperformance

Performance

qwen3.5:35b-a3b-q4… lfm2.5:latest
Tokens/sec16.718.3
First chunk781 ms981 ms
TTFT30.0 s981 ms
Load time19.9 s8.0 s
Memory usage21.8 GB4.9 GB
Memory %17%21%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
15/50
TTFT
0/20
Memory
30/30

lfm2.5:latest

Speed
43/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
8/20
Coding
0/20
Instruction
4/20
Structured
3/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak 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
View qwen3.5:35b-a3b-q4… details | View lfm2.5:latest 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