Item detail
github.com

colibrì — pure-C inference engine that runs 744B to 2.8T MoE models by treating disk, RAM and VRAM as one memory hierarchy

RepoRadar surfaced colibrì — pure-C inference engine that runs 744B to 2.8T MoE models by treating disk, RAM and VRAM as one memory hierarchy — a developer tool — into the Local Inference section, where it sits at Gold tier with a 'try now' verdict. Its strongest signal is momentum, scored 10.0 out of 10.

Score8.9
Popularity100.0
Risknone
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum10.0
Maturity9.4
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for developers who want to run a frontier-scale open-weight model on hardware they already own instead of renting API access; for people evaluating whether expert streaming is fast enough for their workload before buying GPUs; for systems engineers who want a small, readable codebase where an inference optimization can actually be tested.

Who should use it

developers who want to run frontier-scale open-weight models on hardware they already own people evaluating whether expert streaming is fast enough for their workload before buying GPUs systems engineers who want a small readable codebase where an inference optimization can be tested end to end

Who should skip it

Skip colibrì — pure-C inference engine that runs 744B to 2.8T MoE models by treating disk, RAM and VRAM as one memory hierarchy unless the captured evidence suggests it solves a problem you are actively working on.

About this signal

colibrì — pure-C inference engine that runs 744B to 2.8T MoE models by treating disk, RAM and VRAM as one memory hierarchy is tracked by RepoRadar as a developer tool in the Local Inference section. First seen —; the source record was last checked on 2026-08-30. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for colibrì — pure-C inference engine that runs 744B to 2.8T MoE models by treating disk, RAM and VRAM as one memory hierarchy are momentum (10.0) and workflow potential (10.0), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The colibrì — pure-C inference engine that runs 744B to 2.8T MoE models by treating disk, RAM and VRAM as one memory hierarchy record combines a 8.9/10 composite score with separate popularity (100.0), risk (none), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Questions worth asking before you adopt this

Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.

Risk explanation

The maintainers state there is deliberately no SLA on speed: this is an inference engine and an open research platform, and placement policies are described as measurable experiments rather than guarantees; Throughput figures in the README are maintainer-measured on specific hardware; the same model on a different SSD or GPU can land far from them. 81 open issues at time of review; Large-model use means large downloads and sustained NVMe reads; plan disk capacity before starting; Overlaps in purpose with sqliteai/warp, already covered on RepoRadar. They are independent projects by different authors; colibrì is the larger and more general one (more model families, GPU backends, web dashboard).

Evidence links
Closest alternatives / related signals
local-inference moe expert-streaming c cuda metal nvme llm-serving
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-09-13T05:04:21.529456Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

11 dated snapshots retained from 2026-08-30 through 2026-09-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.9 current · +0.0 net
Repository momentum9.0 current · -1.0 net
GitHub stars (observed)28,691 current · +2,081 net
GitHub stars28,691 exact observation
Versionv1.10.2
Last release2026-09-06T20:47:32Z
Maintenanceactive
Current risknone
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-09-138.99.028,691nonetry nowactive
2026-09-128.99.028,344nonetry nowactive
2026-09-118.910.027,624nonetry nowactive
2026-09-088.99.027,035nonetry nowactive
2026-09-078.910.026,828nonetry nownot recorded
2026-09-058.99.626,809nonetry nowactive
2026-09-048.99.626,809nonetry nowactive
2026-09-038.910.026,647nonetry nownot recorded
2026-09-028.99.026,610nonetry nowactive
2026-09-018.99.026,610nonetry nowactive
2026-08-308.910.0Not recordednonetry nowsource activity not yet measured

Why the record changed

stars changed

Stars changed: 28344 → 28691.

stars changed

Stars changed: 28044 → 28344.

stars changed

Stars changed: 27624 → 28044.

stars changed

Stars changed: 27035 → 27624.

stars changed

Stars changed: 27029 → 27035.

stars changed

Stars changed: 26828 → 27029.

stars changed

Reconstructed from adjacent retained daily snapshots; no upstream cause is inferred. Stars changed: 26809 → 26828.

stars changed

Stars changed: 26647 → 26809.

stars changed

Reconstructed from adjacent retained daily snapshots; no upstream cause is inferred. Stars changed: 26610 → 26647.

stars changed

Stars changed: 26589 → 26610.

stars changed

Stars changed: 26572 → 26589.

stars changed

Stars changed: 26563 → 26572.