amd-olmo-1b-sft
LM-STUDIO GGUFolmo · 1B · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
Global Score
44 vs 66
Hardware Fit
75 vs 91
Quality Score
30 vs 55
Hardware
amd-olmo-1b-sft qwen3.8-27b-mlx
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M5 Max
Cores418
RAM16 GB64 GB
GPUIntel(R) HD Graphics 5500Apple M5 Max
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
amd-olmo-1b-sft qwen3.8-27b-mlx
Tokens/sec9.233.2
First chunk2093 ms7 ms
TTFT2.1 s311 ms
Load timeN/AN/A
Memory usage0.7 GB0.5 GB
Memory %4%1%
HW Fit Score Breakdown
amd-olmo-1b-sft
Speed
30/50
TTFT
19/20
Memory
26/30
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
Quality
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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