Back to leaderboard

qwen3.8:27b-bf16

OLLAMA GGUF

qwen35 · 27.3B · BF16

Excellent

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

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 10, 2026 · Apple M4

Global Score
85 vs 66
Hardware Fit
77 vs 34
Quality Score
88 vs 80

Hardware

qwen3.8:27b-bf16 qwen3.5:27b
MachineDell Inc. PowerEdge XE8545Mac mini
CPUAMD EPYC 7713 64-Core ProcessorApple M4
Cores12810
RAM1007 GB24 GB
GPUGA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]Apple M4
OSRocky Linux 8.10macOS 26.3
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.8:27b-bf16 qwen3.5:27b
Tokens/sec27.24.0
First chunk237 ms1655 ms
TTFT237 ms1.7 s
Load time43.8 s12.9 s
Memory usage68.8 GB21.3 GB
Memory %7%89%

HW Fit Score Breakdown

qwen3.8:27b-bf16

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

qwen3.5:27b

Speed
8/50
TTFT
20/20
Memory
6/30

Quality

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

qwen3.5:27b

Reasoning
16/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.8:27b-bf16 details | View qwen3.5:27b 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