Back to leaderboard

qwen3.6-27b-mtp-pi-reasoning

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
85 vs 37
Hardware Fit
80 vs 73
Quality Score
87 vs 22

Hardware

qwen3.6-27b-mtp-pi… deepseek-r1:1.5b
MachineASUSLENOVO 20L7CTO1WW
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorIntel Core™ i5-8350U
Cores168
RAM31 GB23 GB
GPUNVIDIA GeForce RTX 4090, RaphaelKaby Lake-R GT2 [UHD Graphics 620]
OScachyos rollingFedora Linux 43
Archx64x64
Power Modeperformancelow-power

Performance

qwen3.6-27b-mtp-pi… deepseek-r1:1.5b
Tokens/sec42.218.4
First chunk33 ms593 ms
TTFT366 ms30.0 s
Load timeN/A3.8 s
Memory usage24.6 GB1.0 GB
Memory %81%4%

HW Fit Score Breakdown

qwen3.6-27b-mtp-pi-reas…

Speed
50/50
TTFT
20/20
Memory
10/30

deepseek-r1:1.5b

Speed
43/50
TTFT
0/20
Memory
30/30

Quality

qwen3.6-27b-mtp-pi-reas…

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

deepseek-r1:1.5b

Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Weak
View qwen3.6-27b-mtp-pi… details | View deepseek-r1:1.5b 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