Machine
Gtx 1050 · Core i5-7300HQ #74871034
22 runs of 9 models since Oct 12, 2026. Last run Nov 19, 2026.
22
runs
9
models
19
configs
3
configs run 2+ times
Hardware
- GPU
- NVIDIA GeForce GTX 1050 2 GB
- CPU
- Intel(R) Core(TM) i5-7300HQ CPU @ 2.50GHz 4 cores
- RAM
- 15 GB
- OS
- Ubuntu 26.04.1 LTS
- Tools
- LM Studio 22
- Client
- 0.4.99
Models on this machine
One dot per model, at its best config. Up is better answers, right is faster. Time to finish counts every token the model wrote, thinking included, so a model that talks a lot ends up further left.
Best trade-off: quality 60+, and nothing else here is both faster and betterOther models · dot size = number of runs
Medians of each model's best config, 9 models.
Best config per model
sort
Runs with the same model, quant, tool, context, thinking and KV cache count as one config. Numbers are the median of its runs, and each dot is one run on the 0–100 quality scale. ★ marks the best config with at least 2 rated runs.
configrunsqualityeach runspeed
nvidia/nemotron-3-nano-4b
3 runs · 3 configs
ternary-bonsai-2-2b
4 runs · 4 configs
qwen/qwen3-1.7b
2 runs · 2 configs
smollm3-3b
1 run · 1 config
qwen3.5-2b
3 runs · 2 configs
★ bestQ4_K_MLM Studio16k ctxthinking off
×2 runs
37.737.4–38.0
steady
14.9 tok/s
14.2–15.6
llama-3.2-3b-instruct
3 runs · 3 configs
qwen2.5-1.5b-instruct
2 runs · 1 config
★ bestQ6_KLM Studio8k ctxthinking default
×2 runs
29.327.0–31.5
steady
16.8 tok/s
9.6–23.9
phi-3.1-mini-4k-instruct
2 runs · 1 config
★ bestIQ3_MLM Studio8k ctxthinking default
×2 runs
26.823.3–30.2
steady
3.4 tok/s
3.1–3.8
gemma-3b-it-expanded
2 runs · 2 configs
Compare with another machine
Run history
Nov 19, 2026
07:45gemma-3b-it-expandedLM Studio9.3 tok/s10.707:40gemma-3b-it-expandedLM Studio9.2 tok/s14.3Nov 11, 2026
16:52qwen3.5-2bLM Studio16.0 tok/s42.814:03llama-3.2-3b-instructLM Studio6.9 tok/s27.913:37llama-3.2-3b-instructLM Studio6.2 tok/s30.313:17llama-3.2-3b-instructLM Studio6.5 tok/s31.513:00qwen3.5-2bLM Studio15.6 tok/s38.0Nov 10, 2026
17:16smollm3-3bLM Studio6.0 tok/s37.9Oct 30, 2026
10:04ternary-bonsai-2-2bLM Studio39.8 tok/s31.109:55ternary-bonsai-2-2bLM Studio40.0 tok/s44.109:28ternary-bonsai-2-2bLM Studio38.1 tok/s35.609:13ternary-bonsai-2-2bLM Studio38.4 tok/s30.1Oct 28, 2026
22:49qwen2.5-1.5b-instructLM Studio9.6 tok/s27.011:47qwen3-1.7bLM Studio20.0 tok/s41.511:24qwen3-1.7bLM Studio19.5 tok/s35.206:22phi-3.1-mini-4k-instructLM Studio3.1 tok/s30.2Show all 22 runs ▾Show fewer ▴
Oct 24, 2026
15:55qwen3.5-2bLM Studio14.2 tok/s37.4