Can a cheap model install and use TayHCode/sysone-cpu?

Newest observation per platform and model. Revisions, runtimes and operations can differ; this is not a ranking. Earlier observations remain in the full history.

Works on some setups

README claims checked out on 4 recorded setups. Other recorded outcomes appear below; untested combinations remain unknown.

Answers apply to each recorded setup, revision and operation. Earlier observations remain in Run details.

Works with my model and platform?
Platform	Haiku	Luna
Linux	yes	yes
Windows	yes	blocked: setup step
macOS	yes	partly checked

Linux / Haiku 5.5: yes · Oct 22, 2026 · c236055c37fc · claude-code / 2.1.300 (Claude Code)
Recorded operation: <guest-path> run --no-project --python.venv python benchmarks/bench_laya_cpu.py --model.cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output.cache/probe-run.json

Linux / Luna: yes · Oct 22, 2026 · c236055c37fc · codex / codex-cli 0.163.0
Recorded operation: .tools/uv run --no-project --python.venv python benchmarks/bench_laya_cpu.py --model.cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3…

Windows / Haiku 5.5: yes · Oct 22, 2026 · c236055c37fc · claude-code / 2.1.300 (Claude Code)
Recorded operation: 'C:\coldpass\workspace\.tools\uv.exe' run --no-project --python.venv python benchmarks/bench_laya_cpu.py --model.cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3…

Windows / Luna: blocked: setup step · Oct 22, 2026 · c236055c37fc · codex / codex-cli 0.163.0
Recorded operation: partial checks

macOS / Haiku 5.5: yes · Oct 22, 2026 · c236055c37fc · claude-code / 2.1.300 (Claude Code)
Recorded operation: <guest-path> run --no-project --python.venv python benchmarks/bench_laya_cpu.py --model.cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output.cache/probe-first-run.json

macOS / Luna: partly checked · Oct 22, 2026 · c236055c37fc · codex / codex-cli 0.163.0
Recorded operation: .tools/uv run --no-project --python.venv python benchmarks/bench_laya_cpu.py --model.cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3…

Does what it says

1 of 1 claims checked out

The quickstart runs the PyTorch FP32 benchmark on CPU: Real input produced the expected result: wrote .cache/claim-first-run.json
Source: The quickstart uses PyTorch FP32.
Input: quickstart benchmark command with output .cache/claim-first-run.json
Expected: wrote .cache/claim-first-run.json
Command: <guest-path> run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/claim-first-run.json
Observed: wrote .cache/claim-first-run.json

MCP

Local or hosted

local

Local: runs on your machine

Needs keys or browser

None seen

Maintained

Maintained

actively maintained: last commit 3 days ago; 4 commits and 3 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases

Last commit Oct 18, 2026

Setup time

8 min 23 s

8 min 23 s to a working result

Issue

none found in confirmed setups

Examples

2 of 2 ran as expected

Local stdlib unit tests from the README Local checks section: command completed successfully
Source: README.md Local checks
Input: python3 -m unittest discover -s tests -q
Expected: 19 tests OK
Command: /opt/homebrew/bin/python3 -m unittest discover -s tests -q
Observed: ---------------------------------------------------------------------- Ran 19 tests in 0.014s OK
Syntax check from the README Local checks section: command completed successfully
Source: README.md Local checks
Input: python3 scripts/check_syntax.py
Expected: Python syntax checked.
Command: <guest-path> scripts/check_syntax.py
Observed: Python syntax checked.

Evidence

README behavior checked

Agent interfaces

CLI

Observed interfaces were exercised by the checker. Documentation alone does not confirm compatibility.

Tested with

Claude Code / Haiku 5.5

macOS: Claude Code / Haiku 5.5 · agent 2.1.300 (Claude Code) · Checked operation passed · Oct 22, 2026 on c236055c37fc

Each entry describes its recorded operation and source revision. Other agent clients were not tested.

Safety

Something to look at: writes outside the project folder by <guest-path>

Review signals across current setups: connection review, outside write.

Repository processes attempted these non-loopback connections; proxies can hide the final hostname. 74 distinct locations. 2 findings. 39 attributed processes.

Repository processes attempted these writes outside documented output/cache paths. 26 distinct locations. 1 attributed processes.

PID 2231: <guest-path> · <guest-path>

Full event, path and process lists for each observed setup:

Haiku 5.5 (claude-haiku-5-5)

Checked operation passed.

Operation: <guest-path> run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/probe-run.json

Recorded scope: product operation

Agent-reported scope: Run the sysone-cpu PyTorch FP32 quickstart: download and verify the pinned English typed-decisions checkpoint, then run the CPU benchmark on synthetic ticket questions and write its results JSON

run: TayHCode--sysone-cpu-claude-haiku-5-5-1792644887338465139
date: Oct 22, 2026
source commit: c236055c37fc05a0e3f5e9a2933dd8eb946e4f89
test version: readme-1924d8f529c6fc4500abb29916f5c9ac942027957e7b82d725d5610040cd3b4a
purpose: Initial run
platform: linux
reasoning / service tier: low / not recorded
recorded resources: 4096 MiB RAM, 2 CPUs, 32768 MiB disk
model / version: claude-haiku-5-5 / claude-haiku-5-5
agent runtime / version: claude-code / 2.1.300 (Claude Code)
checker: PASS · cli
Recorded source: https://github.com/TayHCode/sysone-cpu
Backend: hyperv
Tool transport: mcp-assigned-vm
Requested source pin (not an observed revision): {"commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "url": "https://github.com/TayHCode/sysone-cpu"}
time to checked operation: 530.6s
total attempt: 564.8s
reported cost (usage complete): $0.014448

run JSON · checker evidence · agent report + check · transcript excerpt · error excerpt unavailable

Checked operation passed.

Operation: 'C:\coldpass\workspace\.tools\uv.exe' run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/probe-bench.json-checker-cd5cb4bb7eb1424eb6745c483e03ccca

Recorded scope: product operation

Agent-reported scope: PyTorch FP32 CPU quickstart: install, download pinned typed-decisions checkpoint, run CPU benchmark, parity collect, local syntax check

run: TayHCode--sysone-cpu-claude-haiku-5-5-1792649286403655136
date: Oct 22, 2026
source commit: c236055c37fc05a0e3f5e9a2933dd8eb946e4f89
test version: readme-1924d8f529c6fc4500abb29916f5c9ac942027957e7b82d725d5610040cd3b4a
purpose: Initial run
platform: windows
reasoning / service tier: low / not recorded
recorded resources: 4096 MiB RAM, 2 CPUs, 32768 MiB disk
model / version: claude-haiku-5-5 / claude-haiku-5-5
agent runtime / version: claude-code / 2.1.300 (Claude Code)
checker: PASS · cli
Recorded source: https://github.com/TayHCode/sysone-cpu
Backend: hyperv
Tool transport: mcp-assigned-vm
Requested source pin (not an observed revision): {"commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "url": "https://github.com/TayHCode/sysone-cpu"}
time to checked operation: 914.0s
total attempt: 992.5s
reported cost (usage complete): $0.046992

run JSON · checker evidence · agent report + check · transcript excerpt · error excerpt unavailable

Checked operation passed.

Recorded scope: product operation

Agent-reported scope: Run the README quickstart PyTorch FP32 CPU benchmark on the pinned sysone-cpu checkpoint, producing answers, latency and memory in a JSON file

run: TayHCode--sysone-cpu-claude-haiku-5-5-1792690379850316428
date: Oct 22, 2026
source commit: c236055c37fc05a0e3f5e9a2933dd8eb946e4f89
test version: readme-71af40079ee68fdda131463405700e8219a99ea96bf0185ac605d5ecffaf5971
purpose: Test repair rerun
platform: macos
reasoning / service tier: low / not recorded
recorded resources: 4096 MiB RAM, None CPUs, 32768 MiB disk
model / version: claude-haiku-5-5 / claude-haiku-5-5
agent runtime / version: claude-code / 2.1.300 (Claude Code)
checker: PASS · cli
Recorded source: https://github.com/TayHCode/sysone-cpu
Backend: tart
Tool transport: mcp-assigned-vm
Requested source pin (not an observed revision): {"commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "url": "https://github.com/TayHCode/sysone-cpu"}
time to checked operation: 503.2s
total attempt: 538.6s
reported cost (usage complete): $0.014630

run JSON · checker evidence · agent report + check · transcript excerpt · error excerpt unavailable

Luna (gpt-6-luna)

Checked operation passed.

Operation: .tools/uv run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/replay-run.json-checker-816b4bc112054695ac5a0bff5a114001

Recorded scope: product operation

Agent-reported scope: Run pinned Laya typed-decisions inference and CPU benchmark

run: TayHCode--sysone-cpu-gpt-6-luna-1792683877827961506
date: Oct 22, 2026
source commit: c236055c37fc05a0e3f5e9a2933dd8eb946e4f89
test version: readme-1002bc876f0002f622e14f9c5b99f9f66721fccc0356f4d53ed24f2f79a3ac5d
purpose: Initial run
platform: linux
reasoning / service tier: low / standard
recorded resources: 4096 MiB RAM, 2 CPUs, 32768 MiB disk
model / version: gpt-6-luna / gpt-6-luna
agent runtime / version: codex / codex-cli 0.163.0
checker: PASS · cli
Recorded source: https://github.com/TayHCode/sysone-cpu
Backend: hyperv
Tool transport: mcp-assigned-vm
Requested source pin (not an observed revision): {"commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "url": "https://github.com/TayHCode/sysone-cpu"}
time to checked operation: 342.1s
total attempt: 365.7s
reported cost: Not reported; not assumed to be zero.

run JSON · checker evidence · agent report + check · transcript excerpt · error excerpt unavailable

The recorded outcome is unverified; see the linked evidence.

Operation: partial checks

Agent-reported scope: README Quickstart: PyTorch FP32 benchmark on synthetic ticket inputs

run: TayHCode--sysone-cpu-gpt-6-luna-1792685264697697627
date: Oct 22, 2026
source commit: c236055c37fc05a0e3f5e9a2933dd8eb946e4f89
test version: readme-1002bc876f0002f622e14f9c5b99f9f66721fccc0356f4d53ed24f2f79a3ac5d
purpose: Initial run
platform: windows
reasoning / service tier: low / standard
recorded resources: 4096 MiB RAM, 2 CPUs, 32768 MiB disk
model / version: gpt-6-luna / gpt-6-luna
agent runtime / version: codex / codex-cli 0.163.0
checker: PASS
Recorded source: https://github.com/TayHCode/sysone-cpu
Backend: hyperv
Tool transport: mcp-assigned-vm
Requested source pin (not an observed revision): {"commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "url": "https://github.com/TayHCode/sysone-cpu"}
time to working: Not established by this run.
total attempt: 323.8s
reported cost: Not reported; not assumed to be zero.

run JSON · checker evidence · agent report + check · transcript excerpt · error excerpt unavailable

The recorded outcome is unverified; see the linked evidence.

Operation: .tools/uv run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .coldpass/replayed-benchmark.json-checker-73bc33ade4144276bc340c195fd662fa

Recorded scope: product operation

Agent-reported scope: Run the README PyTorch FP32 CPU inference benchmark

run: TayHCode--sysone-cpu-gpt-6-luna-1792689385890807813
date: Oct 22, 2026
source commit: c236055c37fc05a0e3f5e9a2933dd8eb946e4f89
test version: readme-0f3d0bf16b16cf3f0e7a538608f68c653dedb635064823cab4ef3c773fbbd53f
purpose: Test repair rerun
platform: macos
reasoning / service tier: low / standard
recorded resources: 4096 MiB RAM, None CPUs, 32768 MiB disk
model / version: gpt-6-luna / gpt-6-luna
agent runtime / version: codex / codex-cli 0.163.0
checker: PASS · cli
Recorded source: https://github.com/TayHCode/sysone-cpu
Backend: tart
Tool transport: mcp-assigned-vm
Requested source pin (not an observed revision): {"commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "url": "https://github.com/TayHCode/sysone-cpu"}
time to working: Not established by this run.
total attempt: 498.2s
reported cost: Not reported; not assumed to be zero.

run JSON · checker evidence · agent report + check · transcript excerpt · error excerpt unavailable

Works on some setups

Haiku 5.5 (claude-haiku-5-5)

Luna (gpt-6-luna)

More Coldpass questions