<!-- Source: https://digitalweaver.ai/cloud-or-local/ -->

ONE WORKSPACE. TWO DIRECTIONS.

# Your documents. Your choice. Cloud or local.

Check an agreement. Explain a charge. Find what is still missing. AMBER connects your question with the relevant document passages; the model helps turn them into an answer you can review.

[Discuss your documents ↗](https://digitalweaver.ai/#contact) [Compare the two options](https://digitalweaver.ai/cloud-or-local/#options)

AMBER WORKSPACES

- 01 Your documents
- 02 AMBER selects relevant passages
- 03 Gemini in the cloud · Qwen locally
- 04 An answer with sources to inspect

## Choose where the model works.

Start with the way your team works, the information it handles and the equipment it has.

Gemini · cloud

### For a responsive working conversation.

The answer model runs with the provider. Your team uses AMBER in a browser, without a local machine sized to run the model.

Selected document passages are sent to the provider to prepare the answer.

**Observed response times:** 2–4 seconds for simple requests; 17–36 seconds for more involved questions.

**What to budget for:** Model usage charges, application hosting and maintenance.

Qwen · local

### For analysis on your own equipment.

Our trials show that a local model can work with agreements, AML materials and legal documents. This route suits teams that want the answer model on their own infrastructure.

The local route was tested in research. We agree the complete data flow and prepare the deployment for each environment.

**Observed response times:** Around 70 seconds typically in our public-document trial.

**What to budget for:** Suitable hardware, electricity and maintenance, alongside the application.

Times come from different studies and tasks. They illustrate the experience, not a direct speed comparison or a delivery promise.

## What we observed.

Six document tasks. The same supplied evidence. Five local models, with Gemini as a cloud reference.

Requirements met in the six-task comparison

Gemini 3.8 Flash high 34  / 34

Qwen 3.6-35B-A3B Q4 30  / 34

Ornith 1.5-35B-A3B Q4 29  / 34

Gemma 4-26B-A4B Q4 26  / 34

Nemotron 3.5 Lightning Q4 19  / 34

GLM 4.7 Flash Q4 12  / 34

34 individual checks across six prepared tasks. These scores are not the percentage of fully correct answers.

### Gemini met all 34 checks in this comparison.

Qwen met 30. It handled useful calculations and interpretation, but needed closer review of sources and answer completeness.

Check important conclusions and their sources with every model.

[About these observations ↓](https://digitalweaver.ai/cloud-or-local/#method)

## Start with a useful question.

01

### Check the terms

Which agreement applies, and what changed in the amendment?

02

### Explain a charge

What remains payable after the credit already applied?

03

### Review the evidence

What do these ownership records establish, and what is still missing?

About these observations

Research observations · September 2026

The six-task comparison used prepared documents and the same drafting instructions. Gemini 3.8 Flash high met 34/34 checks; Qwen3.6-35B-A3B, with thinking off, met 30/34. Model settings differed. The documents were supplied directly: this comparison measures the answers, not a gain attributable to AMBER search.

Task-by-task results

Model | Requirements met | Complete cases | Median time | What to consider |

Gemini 3.8 Flash high Cloud reference

| 34 / 34 | 6 / 6 | Not comparable | Met all measured requirements in this sample; important conclusions still need review. |

Qwen 3.6-35B-A3B Q4 | 30 / 34 | 3 / 6 | 56.3 s | Highest local score in this sample; omitted required details and the historical comparison. |

Ornith 1.5-35B-A3B Q4 | 29 / 34 | 2 / 6 | 35.9 s | Close to Qwen, with shorter responses; double-counted a credit and overstated one ownership share. |

Gemma 4-26B-A4B Q4 | 26 / 34 | 1 / 6 | 22.5 s | Shortest local median here; double-counted a credit and omitted required distinctions. |

Nemotron 3.5 Lightning Q4 | 19 / 34 | 0 / 6 | 29.5 s | Errors in amounts, party identification and source references. |

GLM 4.7 Flash Q4 | 12 / 34 | 0 / 6 | 23.0 s · attempts | Five final answers delivered; numerical errors and one answer cut off at the output limit. |

A complete case meets every task requirement and the application’s source-reference and comparison rules. Zero complete cases does not mean every statement was wrong. These six prepared tasks are observations, not a general model ranking.

Local medians cover drafting plus source checking on the same six supplied contexts, excluding retrieval, import and scan processing. GLM delivered five of six final answers; its 23.0-second median includes the failed 194.9-second attempt. The separate Vertex times above are not timings for this six-task Gemini result.

Primary, strict scores are shown. Alternative interpretations of individual requirements give Ornith 30/34 and 3/6 complete cases, Nemotron 20/34, or GLM 13/34. These alternatives do not replace the primary assessment.

Where each model succeeded or stumbled

Task | Gemini 3.8 Flash high | Qwen 3.6-35B-A3B Q4 | Ornith 1.5-35B-A3B Q4 | Gemma 4-26B-A4B Q4 | Nemotron 3.5 Lightning Q4 | GLM 4.7 Flash Q4 |

Freight charge correction | 6/6  All six checks met

| 5/6  Correct balance; unsupported claim about the rate’s origin

| 4/6  596 instead of 620: credit deducted twice

| 4/6  596 instead of 620: credit deducted twice

| 1/6  Free waiting time omitted

| 0/6  266 instead of 140 for waiting

|

Earlier contract terms | 6/6  All six checks met

| 5/6  Correct terms; required comparison not accepted

| 5/6  Correct terms; required comparison missing

| 6/6  All six checks met

| 4/6  Retroactive effect denied despite the source

| 5/6  Comparison order reversed

|

Laboratory release | 5/5  All five checks met

| 5/5  All five checks met

| 5/5  All five checks met

| 3/5  Other instrument and lot not explicitly excluded

| 3/5  Same omissions; English instead of German

| 3/5  Other instrument and lot not explicitly excluded

|

Ownership and control | 6/6  All six checks met

| 6/6  All six checks met

| 5/6  72% instead of 36% for one owner

| 5/6  No explicit request for full identifiers

| 6/6  Six criteria met; source declaration missing

| 2/6  25.2% instead of 36%; other shares omitted

|

Pleading review | 6/6  All six checks met

| 4/6  A2 section 2 omitted; supplied court rejected

| 5/6  Court identified, but source and missing-field distinction confused

| 4/6  A2 section 2 and missing attachment link omitted

| 3/6  Wrong company and incomplete clause reference

| 0/6  No final answer: output limit reached

|

Spend and coverage | 5/5  All five checks met

| 5/5  All five checks met

| 5/5  All five checks met

| 4/5  Earlier-record completeness caveat omitted

| 2/5  31,600 instead of 29,600: credit not subtracted

| 2/5  22,000 instead of 29,600

|

Scores count individual requirements. Notes give selected examples; a full score does not guarantee flawless wording or acceptance by every application check.

Cloud times cover eight successful simple or conversational requests (2.12–3.53 seconds) and four complex requests (16.84–36.05 seconds) through Google Vertex on small prepared document sets. Local times come from 18 Polish questions over eight public AML, customs and legal documents: median 69.77 seconds, range 48.28–96.73 seconds. These are separate studies and application versions; import and scan processing are excluded. Concurrent use was not measured.

In the public-document study, Qwen met 50/54 content checks; 10/18 answers met all content, language and source-support requirements (11/18 under an independent review). The trial did not meet its pre-set quality and response-time targets. Local use therefore remains a route to assess in a pilot, with human review.

## Try the question that matters to you.

Bring a small, agreed sample of documents. Together we assess the answer, its sources and the time it takes before choosing the deployment.

[Discuss your documents ↗](https://digitalweaver.ai/#contact)

Public reference materials were used for research. AMBER is not affiliated with the organizations named in those materials.
