Back to leaderboard

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Sep 6, 2026 · Intel Xeon® E5-4650 v2

Global Score
37 vs 81
Hardware Fit
73 vs 63
Quality Score
22 vs 88

Hardware

deepseek-r1:1.5b qwen3.5-35b-a3b-t4…
MachineLENOVO 20L7CTO1WWDell Inc. PowerEdge R820
CPUIntel Core™ i5-8350UIntel Xeon® E5-4650 v2
Cores880
RAM23 GB256 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Microsoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display Adapter
OSFedora Linux 43Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modelow-powerbalanced

Performance

deepseek-r1:1.5b qwen3.5-35b-a3b-t4…
Tokens/sec18.417.2
First chunk593 ms845 ms
TTFT30.0 s845 ms
Load time3.8 s103.1 s
Memory usage1.0 GB21.9 GB
Memory %4%9%

HW Fit Score Breakdown

deepseek-r1:1.5b

Speed
43/50
TTFT
0/20
Memory
30/30

qwen3.5-35b-a3b-t48-c8k…

Speed
16/50
TTFT
17/20
Memory
30/30

Quality

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

qwen3.5-35b-a3b-t48-c8k…

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest