Back to leaderboard

amd-olmo-1b-sft

LM-STUDIO GGUF

olmo · 1B · Q4_K_M

Marginal

Mar 8, 2026 · Intel Core™ i5-5300U

glm-4.7-flash:q4_K_M

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
44 vs 81
Hardware Fit
75 vs 89
Quality Score
30 vs 77

Hardware

amd-olmo-1b-sft glm-4.7-flash:q4_K_M
MachineLENOVO 20BUS00700ASUS
CPUIntel Core™ i5-5300UIntel Core™ i5-14600KF
Cores420
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500NVIDIA GeForce RTX 4070 Ti SUPER
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

amd-olmo-1b-sft glm-4.7-flash:q4_K_M
Tokens/sec9.235.1
First chunk2093 ms440 ms
TTFT2.1 s440 ms
Load timeN/A11.6 s
Memory usage0.7 GB18.4 GB
Memory %4%58%

HW Fit Score Breakdown

amd-olmo-1b-sft

Speed
30/50
TTFT
19/20
Memory
26/30

glm-4.7-flash:q4_K_M

Speed
49/50
TTFT
20/20
Memory
20/30

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

glm-4.7-flash:q4_K_M

Reasoning
13/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

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