Back to leaderboard

qwen3.8:27b-q8_0

OLLAMA GGUF

qwen35 · 27.3B · Q8_0

Excellent

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

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
89 vs 67
Hardware Fit
88 vs 77
Quality Score
89 vs 63

Hardware

qwen3.8:27b-q8_0 llama3.2:3b
MachineDell Inc. PowerEdge XE8545LENOVO 20U30029MB
CPUAMD EPYC 7713 64-Core ProcessorIntel Core™ i5-10210U
Cores1288
RAM1007 GB15 GB
GPUGA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]CometLake-U GT2 [UHD Graphics]
OSRocky Linux 8.10Pop 24.04 LTS
Archx64x64
Power Modeunknownlow-power

Performance

qwen3.8:27b-q8_0 llama3.2:3b
Tokens/sec40.010.0
First chunk177 ms1166 ms
TTFT177 ms1.2 s
Load time24.7 s6.8 s
Memory usage51.0 GB3.8 GB
Memory %5%25%

HW Fit Score Breakdown

qwen3.8:27b-q8_0

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

llama3.2:3b

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

Quality

qwen3.8:27b-q8_0

Reasoning
18/20
Coding
19/20
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

llama3.2:3b

Reasoning
11/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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