Back to leaderboard

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

unsloth/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q3_K_M

Excellent

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

Global Score
37 vs 85
Hardware Fit
73 vs 79
Quality Score
22 vs 88

Hardware

deepseek-r1:1.5b unsloth/qwen3.6-35…
MachineLENOVO 20L7CTO1WWSystem manufacturer
CPUIntel Core™ i5-8350UAMD Ryzen 7 5800X 8-Core Processor
Cores816
RAM23 GB31 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Navi 44 [Radeon RX 9060 XT]
OSFedora Linux 43Ubuntu 26.04.1 LTS
Archx64x64
Power Modelow-powerperformance

Performance

deepseek-r1:1.5b unsloth/qwen3.6-35…
Tokens/sec18.423.5
First chunk593 ms54 ms
TTFT30.0 s457 ms
Load time3.8 sN/A
Memory usage1.0 GB18.3 GB
Memory %4%59%

HW Fit Score Breakdown

deepseek-r1:1.5b

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

unsloth/qwen3.6-35b-a3b

Speed
38/50
TTFT
20/20
Memory
21/30

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

unsloth/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View deepseek-r1:1.5b details | View unsloth/qwen3.6-35… 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