{"schema_version":"0.1","id":"50e2b413-774f-472d-8b80-84fd1f1adb76","display_name":"Saoirse Byrne","handle":"saoirse-dev","avatar_url":"https://i.pravatar.cc/160?img=36","positioning":"Reviews local coding models on camera, with the runs to back them.","topics":["Coding agents","Local LLMs","Model reviews"],"region":"Dublin, Ireland","languages":{"content":["English"],"communication":["English"]},"time_zone":"Europe/Dublin","accounts":[{"platform":"youtube","handle":"saoirse-dev","url":null,"ownership_status":"self_reported","metric_snapshot":{"metric":"subscribers","value":34200,"unit":null,"period":null,"sample_size":null,"as_of":"2026-11-03T08:05:30.284Z","source_type":"self_reported","historical":false},"evidence":[]},{"platform":"x","handle":"saoirse-dev","url":null,"ownership_status":"self_reported","metric_snapshot":{"metric":"followers","value":18900,"unit":null,"period":null,"sample_size":null,"as_of":"2026-11-03T03:05:30.284Z","source_type":"self_reported","historical":false},"evidence":[]}],"works":[{"id":"cd02f9c9-d319-40a8-89f9-777a65733dd7","type":"video","title":"Five local coding models, one hard bug","role":null,"personal_contribution":null,"outcome":"Qwen3-Coder-30B fixed it in 2 of 3 tries; the rest stalled on the test runner.","limitations":null,"version":null,"links":[],"disclosure":"independent","pinned":true,"run_id":null,"evidence":[{"type":"source_linked","label":"Source linked","scope":"The link points to this creator's published work.","does_not_establish":"Does not establish the numbers in it.","review_status":"pending","version":null,"date":"2026-10-28T03:05:30.284Z"}],"updated_at":"2026-10-28T03:05:30.284Z","date":"2026-10-28","visibility":"public"},{"id":"fe12ce02-8c3f-4ebe-a347-9ddaa38404bf","type":"run","title":"Qwen3-Coder-30B-A3B-Instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3-coder:30b-a3b-q4_K_M, NVIDIA GeForce RTX 4090 · 24 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 224.4 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"535fb310-ef07-4be0-b735-f45da65ab71d","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-11-06T05:53:30.284Z"}],"updated_at":"2026-11-06T05:53:30.284Z","date":"2026-11-06","visibility":"public"},{"id":"838180e6-9577-483e-9c1f-e354643b58ab","type":"run","title":"gemma-3-4b-it on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for gemma3:4b-it-q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 2/3 · tool-flight not supported · needle-8k 2/3 · 229.7 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"33a761e7-63f9-4017-abf7-ed043300cee9","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 2 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-11-04T19:10:18.721Z"}],"updated_at":"2026-11-04T19:10:18.721Z","date":"2026-11-04","visibility":"public"},{"id":"bfb3f901-f4fe-4e4e-aee4-44ba629590f7","type":"run","title":"Qwen3-8B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:8b-q4_K_M, Apple M4 Max · 128 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 65.7 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"47b178f7-af73-4f41-99f9-72138cb54895","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-11-02T17:04:54.185Z"}],"updated_at":"2026-11-02T17:04:54.185Z","date":"2026-11-02","visibility":"public"},{"id":"9867c4d1-518f-4a3f-be66-818e9cdfe6fc","type":"run","title":"Qwen3-Coder-30B-A3B-Instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3-coder:30b-a3b-q4_K_M, NVIDIA GeForce RTX 4090 · 24 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 2/3 · 216.2 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"b9574f12-5dd7-4c71-a846-e9576e6601f2","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-28T17:20:07.440Z"}],"updated_at":"2026-10-28T17:20:07.440Z","date":"2026-10-28","visibility":"public"},{"id":"bf539215-56e4-4f71-af05-506e7d9f218b","type":"run","title":"Qwen3-Coder-30B-A3B-Instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3-coder:30b-a3b-q4_K_M, Apple M4 Max · 128 GB.","outcome":"code-intervals 2/3 · tool-flight 3/3 · needle-8k 3/3 · 110.4 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"89ec09ee-85d3-4c73-a620-1e5b7917c90f","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-23T10:47:14.535Z"}],"updated_at":"2026-10-23T10:47:14.535Z","date":"2026-10-23","visibility":"public"},{"id":"f49fcb82-c1f5-426c-92c8-1f1d531c1db2","type":"run","title":"Qwen3-30B-A3B-Instruct-2507 on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:30b-a3b-instruct-2507-q4_K_M, NVIDIA GeForce RTX 4090 · 24 GB.","outcome":"code-intervals 3/3 · tool-flight 2/3 · needle-8k 3/3 · 215.8 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"627bc421-0979-448e-b34e-deba65d77bcf","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-18T08:42:55.932Z"}],"updated_at":"2026-10-18T08:42:55.932Z","date":"2026-10-18","visibility":"public"},{"id":"a33c944a-735b-45d1-8e63-6e2043f63035","type":"video","title":"Launch review: the Tern T2 dev kit","role":null,"personal_contribution":null,"outcome":"Delivered on brief; ran three suites on the kit live.","limitations":null,"version":null,"links":[],"disclosure":"paid_collaboration","pinned":false,"run_id":null,"evidence":[{"type":"delivery_accepted","label":"Delivery accepted","scope":"The client accepted the delivery against the agreed brief.","does_not_establish":"Does not establish audience reach.","review_status":"passed","version":null,"date":"2026-10-17T05:05:30.284Z"}],"updated_at":"2026-10-17T05:05:30.284Z","date":"2026-10-17","visibility":"public"},{"id":"d6fe3d4a-05fc-4303-9458-732a5580643c","type":"run","title":"Qwen3-8B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:8b-q4_K_M, Apple M4 Max · 128 GB.","outcome":"code-intervals 2/3 · tool-flight 2/3 · needle-8k 3/3 · 70.0 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"d3af54b6-fb30-446a-a1ba-aad326f519b3","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-13T12:03:36.354Z"}],"updated_at":"2026-10-13T12:03:36.354Z","date":"2026-10-13","visibility":"public"},{"id":"2bb95246-ef99-47bf-839c-579da7f41a2c","type":"run","title":"Qwen3-Coder-30B-A3B-Instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3-coder:30b-a3b-q4_K_M, NVIDIA GeForce RTX 4090 · 24 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 207.0 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"a61b9380-2c0b-4833-9c23-1c471f20b8bf","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-08T09:51:10.417Z"}],"updated_at":"2026-10-08T09:51:10.417Z","date":"2026-10-08","visibility":"public"},{"id":"186c09e4-c892-4bcd-9cd2-5414be62db31","type":"video","title":"gpt-oss-20b on a 4090: what the speed numbers hide","role":null,"personal_contribution":null,"outcome":null,"limitations":null,"version":null,"links":[],"disclosure":"independent","pinned":false,"run_id":null,"evidence":[{"type":"source_linked","label":"Source linked","scope":"The link points to this creator's published work.","does_not_establish":"Does not establish the numbers in it.","review_status":"pending","version":null,"date":"2026-10-06T08:05:30.284Z"}],"updated_at":"2026-10-06T08:05:30.284Z","date":"2026-10-06","visibility":"public"},{"id":"c4389169-3b7b-42fa-b3a3-f80d27c8b519","type":"run","title":"MiniCPM5-2B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for openbmb/minicpm5-2b:q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 3/3 · tool-flight 1/3 · needle-8k 1/3 · 301.4 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"3dafb745-1596-4226-bfd3-c06c5b5cf379","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 3 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-05T07:07:36.687Z"}],"updated_at":"2026-10-05T07:07:36.687Z","date":"2026-10-05","visibility":"public"},{"id":"b8679a8e-ec7b-41a9-b823-aa384842f727","type":"run","title":"Qwen3-8B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:8b-q4_K_M, Apple M4 Max · 128 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 69.6 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"8f967f28-40f5-41cd-b029-4130d726b0c9","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-03T11:42:44.945Z"}],"updated_at":"2026-10-03T11:42:44.945Z","date":"2026-10-03","visibility":"public"},{"id":"49728579-252a-4100-8070-5fed430631e4","type":"run","title":"Qwen3-8B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:8b-q4_K_M, NVIDIA GeForce RTX 4090 · 24 GB.","outcome":"code-intervals 2/3 · tool-flight 3/3 · needle-8k 3/3 · 141.3 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"b44cc16b-1649-4489-96ed-cb1d55d77827","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-29T02:58:52.305Z"}],"updated_at":"2026-09-29T02:58:52.305Z","date":"2026-09-29","visibility":"public"},{"id":"e619a7aa-70a5-4fed-a790-1076433fca68","type":"run","title":"gpt-oss-20b on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on gpt-oss:20b, Apple M4 Max · 128 GB.","outcome":"code-intervals 1/3 · tool-flight 3/3 · needle-8k 3/3 · 102.0 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · MXFP4","links":[],"disclosure":"not_stated","pinned":false,"run_id":"3b9c6a02-59be-4747-9742-e8a82ac6e14c","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · MXFP4","date":"2026-09-25T11:24:36.984Z"}],"updated_at":"2026-09-25T11:24:36.984Z","date":"2026-09-25","visibility":"public"},{"id":"c219d74b-577a-41cb-8237-40a741d5e056","type":"article","title":"How I test a coding model before I review it","role":null,"personal_contribution":null,"outcome":null,"limitations":null,"version":null,"links":[],"disclosure":"independent","pinned":false,"run_id":null,"evidence":[{"type":"source_linked","label":"Source linked","scope":"The link points to this creator's published work.","does_not_establish":"Does not establish the numbers in it.","review_status":"pending","version":null,"date":"2026-09-22T11:05:30.284Z"}],"updated_at":"2026-09-22T11:05:30.284Z","date":"2026-09-22","visibility":"public"},{"id":"0cb4e46a-ee33-4528-b828-37a42bc10c54","type":"run","title":"gpt-oss-20b on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on gpt-oss:20b, NVIDIA GeForce RTX 4090 · 24 GB.","outcome":"code-intervals 2/3 · tool-flight 2/3 · needle-8k 3/3 · 208.4 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · MXFP4","links":[],"disclosure":"not_stated","pinned":false,"run_id":"16933245-b742-452c-8c47-2ba0409cc970","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · MXFP4","date":"2026-09-20T10:49:35.353Z"}],"updated_at":"2026-09-20T10:49:35.353Z","date":"2026-09-20","visibility":"public"},{"id":"7e02d7b7-a71b-4d79-9cf6-7ec7e22df6ac","type":"run","title":"Qwen3-14B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:14b-q4_K_M, Apple M4 Max · 128 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"4ab52ee9-cc61-4ad9-93c4-b35ca25bf976","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-14T11:26:08.179Z"}],"updated_at":"2026-09-14T11:26:08.179Z","date":"2026-09-14","visibility":"public"},{"id":"bf74f239-9e85-4520-8c4b-e806b80910c8","type":"run","title":"Qwen3-Coder-30B-A3B-Instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3-coder:30b-a3b-q4_K_M, NVIDIA GeForce RTX 4090 · 24 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 207.2 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"72a5bf0e-3e1d-43c0-a3f4-c2219e719955","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-09T14:15:32.818Z"}],"updated_at":"2026-09-09T14:15:32.818Z","date":"2026-09-09","visibility":"public"},{"id":"591362e4-c1bc-4d58-aa85-548428aa51a9","type":"run","title":"Qwen3-14B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:14b-q4_K_M, Apple M4 Max · 128 GB.","outcome":"code-intervals 3/3 · tool-flight 1/3 · needle-8k 3/3 · 39.1 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"95e97428-f46c-42a6-bb56-e72effebc48a","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-04T01:58:41.786Z"}],"updated_at":"2026-09-04T01:58:41.786Z","date":"2026-09-04","visibility":"public"}],"collaboration":{"formats":["Sponsored review","Launch video","Workshop"],"availability":{"slots":2,"month":"December 2026","confirmed_at":"2026-11-02T12:05:30.284Z","unconfirmed":false}},"reputation":{"verified_works":17,"reproductions":0,"tier":"regular"},"updated_at":"2026-11-06T08:05:30.284Z"}