Back to leaderboard

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

qwen3.8:27b-bf16

OLLAMA GGUF

qwen35 · 27.3B · BF16

Excellent

Aug 22, 2026 · AMD EPYC 7713 64-Core Processor

Global Score
61 vs 85
Hardware Fit
85 vs 77
Quality Score
51 vs 88

Hardware

qwen3:0.6b qwen3.8:27b-bf16
MachineLENOVO 20L7CTO1WWDell Inc. PowerEdge XE8545
CPUIntel Core™ i5-8350UAMD EPYC 7713 64-Core Processor
Cores8128
RAM23 GB1007 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]
OSFedora Linux 43Rocky Linux 8.10
Archx64x64
Power Modelow-powerunknown

Performance

qwen3:0.6b qwen3.8:27b-bf16
Tokens/sec27.027.2
First chunk597 ms237 ms
TTFT8.7 s237 ms
Load time1.8 s43.8 s
Memory usage0.9 GB68.8 GB
Memory %4%7%

HW Fit Score Breakdown

qwen3:0.6b

Speed
50/50
TTFT
5/20
Memory
30/30

qwen3.8:27b-bf16

Speed
27/50
TTFT
20/20
Memory
30/30

Quality

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate

qwen3.8:27b-bf16

Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3:0.6b details | View qwen3.8:27b-bf16 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