qwen3-1.7b
LM-STUDIO GGUFqwen3 · 1.7B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-5300U
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
19 vs 65
Hardware Fit
64 vs 96
Quality Score
0 vs 52
Hardware
qwen3-1.7b richardyoung/qwyth…
MachineLENOVO 20BUS00700Mac mini
CPUIntel Core™ i5-5300UApple M4 Pro
Cores412
RAM16 GB24 GB
GPUIntel(R) HD Graphics 5500Apple M4 Pro
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3-1.7b richardyoung/qwyth…
Tokens/sec5.925.3
First chunk2111 ms397 ms
TTFT2.1 s397 ms
Load timeN/A6.3 s
Memory usage1.2 GB8.3 GB
Memory %8%34%
HW Fit Score Breakdown
qwen3-1.7b
Speed
21/50
TTFT
19/20
Memory
24/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
Quality
qwen3-1.7b
Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
richardyoung/qwythos-9b…
Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest