Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

llama3.3:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-X925

Global Score
80 vs 73
Hardware Fit
52 vs 51
Quality Score
92 vs 83

Hardware

qwen/qwen3.8-27b llama3.3:70b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M4 MaxCortex-X925
Cores1620
RAM128 GB122 GB
GPUApple M4 MaxDevice 2e12
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen/qwen3.8-27b llama3.3:70b
Tokens/sec16.14.6
First chunk14 ms560 ms
TTFT5.8 s560 ms
Load time8.5 s13.8 s
Memory usage0.0 GB49.5 GB
Memory %0%41%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
17/50
TTFT
5/20
Memory
30/30

llama3.3:70b

Speed
4/50
TTFT
20/20
Memory
27/30

Quality

qwen/qwen3.8-27b

Reasoning
19/20
Coding
16/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

llama3.3:70b

Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen/qwen3.8-27b details | View llama3.3:70b 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