Skip to content

A field guide to local AI

Local intelligence.
Shared experience.

A DGX Spark, an ASUS GX10, an RTX 5090, and a Mac Studio. A working local AI lab, documented through configurations, measured experiments, and the lessons that changed our minds.

CONFIG VERIFIED OCT 23, 2026 / 45 PUBLISHED STUDY RECORDS

Inside the local labIllustrated flow / Oct 23, 2026
Coding + scout + native vision routing through llama-swapDeepSeek V4.1 Flash 1017 · EXL3 · normal routes to DGX Spark + GX10. The two GB10 hosts share an explicitly configured tensor-parallel coder. Every other route uses an individual host. Moving dots illustrate requests, not live activity.DGX SparkGB10 · 128 GBASUS GX10GB10 · 128 GBMac StudioM5 Max · 48 GBRTX 509032 GB GDDR7llama-swapROUTING + RESIDENCYTWO NODES · TENSORFOLD TP2 · FOUR SHARED SLOTS

Coding + scout + native vision

DGX Spark + GX10

DeepSeek V4.1 Flash 1017 · EXL3 · normal

Selectors: coder · scout · vision

524,288 configured · 4 shared slots
Persistent TensorFold TP2 · 32,768 output cap · high reasoning default

Native and routed text/tools/image checks passed. Small matched coding panel tied GLM. Full-window retrieval and concurrent long-context serving remain unqualified. Dated configuration; moving dots illustrate requests.

GB10 systems

2 × 128 GB

DGX Spark + ASUS GX10. DeepSeek EXL3 through TensorFold TP2; four shared inference slots.

Media GPU

RTX 5090

32 GB GDDR7, Ryzen 9 9950X3D, Windows + WSL2.

Apple silicon

M5 Max · 48 GB

Mac Studio, 40 GPU cores. Agent, writing, embeddings, and local inference.

Fresh inspection / Oct 23, 2026

DeepSeek on two GB10 hosts. 4 shared inference slots.

DeepSeek V4.1 Flash 1017 now serves coder, scout and vision through TensorFold on the DGX Spark and ASUS GX10. The matched Hermes panel tied GLM on coding; short capacity probes, memory observations and cache replay have their own limits.

Open the DeepSeek setup guide ↗
Read the latest review ↗

01 / Build your baseline

Find your starting point.

All setup guides

02 / A working lab

Four machines. Deliberate roles.

Hardware & configuration

Current placement is verified from active configuration. Older experiments keep their original hardware and dates.

03 / What the measurements taught us

Match the model to the job.

Explore the visual evidence

Historical / September Studio evaluation

Speed is only one axis.

Protocol & limitations ↗

M5 Max · 40 GPU cores · 48 GB · Sep 22–23, 2026 · thinking off. Lightning here is the evaluated Nemotron artifact. The current SuperQwen alias has no score in this chart.

HumanEval / % ↑

050100080160

Code decode / tok/s →

Coding fallback / MLX 4-bit

95.1%

HumanEval · 156 / 164 tasks passed

All 164 original tasks, one greedy chat sample, original executable tests, no repair or retries. Chat-adapted pass@1; training contamination is possible. Gemma was a writing-role evaluation and did not run this suite.

Speed: median of three short 512-output code probes on a loaded backend. Timing and quality use different prompts; this is not full-task wall time.

The experiment notebook

The fastest model
doesn’t win every job.

In September's Studio evaluation, Lightning decoded faster while Qwen passed more coding tests. Our Spark studies also include reversals, rejected contenders, and optimizations that only helped one workload.

See the experiments

MTP / Spark code

+57.4%

64.1 → 100.9 tok/s
Six draft positions, one quiet slot

MTP / Spark creative

−17.0%

64.6 → 53.6 tok/s
The same switch slowed writing

JUL 11, 2026 / HISTORICAL QWEN3.6 Q6_K / REPEAT SPREAD NOT RETAINED.

Jul → Oct 2026 / Learning in public

The setup changed. The lessons stayed.

All journal notes ↗

Chapter 01 / Jul 11, 2026

+57.4% code / −17.0% creative

Six-position MTP changed two workloads in opposite directions. The optimization became a per-workload decision.

Read the decision ↗

04 / The public journal

The decisions behind the setup.

Read the journal

Agentic repo prompt / Illustrated process

Give the agent a loop.
Keep the evidence.

A bounded improvement becomes a verified change, an independent review decision, and a durable record. The model's decode score measures one small piece of that process.

01 / Inspect

Read the repository instructions and evidence. Choose one useful problem inside the authorized scope.

Use the public repo prompt ↗
The repository improvement loopInspect, implement, verify, review, integrate, and record. Review can hold a change for correction. Integration requires repository policy and authorization. This is a process illustration.01 /Inspect02 /Implement03 /Verify04 /Review05 /Integrate06 /RecordHOLD → CORRECT → VERIFYMERGE → ELIGIBLE INTEGRATION

QABot returns MERGE or HOLD. MergeBot handles eligible squash merges. Authorization and a useful next pass bound the loop.