qwen3.5-0.8b-mlx
LM-STUDIO MLXqwen3_5 · 0.8B · 4bit
Mar 3, 2026 · Apple M4
amd-olmo-1b-sft
LM-STUDIO GGUFolmo · 1B · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
Global Score
55 vs 44
Hardware Fit
87 vs 75
Quality Score
41 vs 30
Hardware
qwen3.5-0.8b-mlx amd-olmo-1b-sft
MachineMacBook AirLENOVO 20BUS00700
CPUApple M4Intel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M4Intel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.5-0.8b-mlx amd-olmo-1b-sft
Tokens/sec68.29.2
First chunk3268 ms2093 ms
TTFT3.3 s2.1 s
Load timeN/AN/A
Memory usage0.6 GB0.7 GB
Memory %2%4%
HW Fit Score Breakdown
qwen3.5-0.8b-mlx
Speed
50/50
TTFT
13/20
Memory
24/30
amd-olmo-1b-sft
Speed
30/50
TTFT
19/20
Memory
26/30
Quality
qwen3.5-0.8b-mlx
Reasoning
8/20
Coding
1/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
amd-olmo-1b-sft
Reasoning
4/20
Coding
2/20
Instruction
11/20
Structured
9/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor 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