Back to leaderboard

lmstudio-community/Phi-4-reasoning-plus-MLX-4bit

LM-STUDIO GGUF
Not Rec.

Mar 5, 2026 · Apple M4

qwen3.8:27b-q8_0

OLLAMA GGUF

qwen35 · 27.3B · Q8_0

Excellent

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

Global Score
33 vs 89
Hardware Fit
74 vs 88
Quality Score
15 vs 89

Hardware

lmstudio-community… qwen3.8:27b-q8_0
MachineMacBook AirDell Inc. PowerEdge XE8545
CPUApple M4AMD EPYC 7713 64-Core Processor
Cores10128
RAM32 GB1007 GB
GPUApple M4GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]
OSmacOS 26.3Rocky Linux 8.10
Archarm64x64
Power Modebalancedunknown

Performance

lmstudio-community… qwen3.8:27b-q8_0
Tokens/sec11.540.0
First chunk670 ms177 ms
TTFT670 ms177 ms
Load timeN/A24.7 s
Memory usage3.0 GB51.0 GB
Memory %9%5%

HW Fit Score Breakdown

lmstudio-community/Phi-…

Speed
24/50
TTFT
20/20
Memory
30/30

qwen3.8:27b-q8_0

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

Quality

lmstudio-community/Phi-…

Reasoning
8/20
Coding
1/20
Instruction
1/20
Structured
1/15
Math
1/15
Multilingual
3/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Weak

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
View lmstudio-community… details | View qwen3.8:27b-q8_0 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