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

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
35 vs 37
Hardware Fit
45 vs 73
Quality Score
30 vs 22

Hardware

qwen3.5:35b-a3b-q4… deepseek-r1:1.5b
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 43
Archx64x64
Power Modebalancedlow-power

Performance

qwen3.5:35b-a3b-q4… deepseek-r1:1.5b
Tokens/sec16.718.4
First chunk781 ms593 ms
TTFT30.0 s30.0 s
Load time19.9 s3.8 s
Memory usage21.8 GB1.0 GB
Memory %17%4%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

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

deepseek-r1:1.5b

Speed
43/50
TTFT
0/20
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

deepseek-r1:1.5b

Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Weak
View qwen3.5:35b-a3b-q4… details | View deepseek-r1:1.5b 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