Skip to main content
← Back to Verdict-4 Model Catalog
Local & MVAI Only ($0/tok)Weight-Modified Fine-Tune (Local Only)

Verdict 4 500M Quill

50-iteration fused LoRA SFT on Qwen2.5-Coder-0.5B-Instruct (~1.34 GiB peak RSS at 32K context) for ultra-constrained 4–8 GB RAM laptops and fast local diagnostics.

Lineage, Provenance & Runtime Specification

Upstream Checkpoint
Qwen/Qwen2.5-Coder-0.5B-Instruct
Upstream License
Apache-2.0
Architecture & Active Params
qwen2 Dense · 0.5B dense
Certified Context / Max Output
32,768 tok / 2,048 tok
Recommended Hardware Tier
4–8 GB CPU-only laptops (~1.34 GiB peak RSS at 32K f16 KV; 2 GB free RAM recommended)
Weight Modification & Audit Proof
Derived from Qwen/Qwen2.5-Coder-0.5B-Instruct (Apache-2.0), quantized Q5_K_M GGUF and 4-bit MLX.

Paired Empirical Evidence (Unmerged Comparators)

Artifact-Bound Benchmark Measurements

Measured on: Local CPU GGUF Q5_K_M (32K f16 KV) · Apple M4 Max

Micro-Tier Baseline & Memory Profile

Comparator: Single-arm release validation (release_manifest.json)

BCB First-100
7/100

Ultra-small 0.5B micro-model tier

CPU 32K Peak RSS
1.34 GiB

Idle 1.13 GiB at 32K f16 KV

Methodology & Caveat: Intended strictly for syntax helpers, small local completions, and sub-2 GB free-RAM environments.

Live Basis P2 Burn & Effective Customer Rate Across Credit Packs

This model runs strictly on local CPU/Apple Silicon hardware ($0.00/tok) and is not billed as a Cloud SKU.

Certified Sampler Contract (§6.2)

Engine Presets & Cryptographic Checksums

  • CRITICAL: MLX build requires strict repeat_penalty = 1.0; LM Studio's default 1.1 degrades/breaks 500m-quill MLX output.
  • Windows and Linux deployments support GGUF Q5_K_M only.

llama.cpp (llama-server)

llama-server \
  -m verdict-4-500m-quill-Q5_K_M.gguf \
  --ctx-size 32768 \
  --temp 0.2 \
  --repeat-penalty 1.0 \
  --port 8080

LM Studio (model.yaml)

# Install at ~/.lmstudio/hub/models/verdict/verdict-4-500m-quill/model.yaml
model: verdict/verdict-4-500m-quill
base: verdict/verdict-4-500m-quill-gguf-q5-k-m/verdict-4-500m-quill-Q5_K_M.gguf
config:
  load:
    fields:
      - key: llm.load.contextLength
        value: 32768
  operation:
    fields:
      - key: llm.prediction.temperature
        value: 0.2
      - key: llm.prediction.repeatPenalty
        value: 1.0
metadataOverrides:
  domain: llm
  architectures: [qwen2]
  compatibilityTypes: [gguf]
  paramsStrings: [0.5B]
  minMemoryUsageBytes: 2000000000
  contextLengths: [32768]
  vision: false
  reasoning: false

Verified Local Artifact Checksums

Binary Weights Staged — Gated on Phase 0b Ed25519 Signing
verdict-4-500m-quill-gguf-q5-k-mGGUF Q5_K_M · 420,086,144 bytes

SHA-256: da959e399993f511bc00bc72d5da44289bd5d20d2c35c83083df07a14de06656

verdict-4-500m-quill-mlx-4bitMLX 4-bit · 278,065,225 bytes

SHA-256: ee37c7811b9502d7a999818c7f2ac83abb9b30d40fbb40babd3d4f39e231d295

weight_set_sha256: c3caeaf2d711b4a27264c7ba896ecf90c776a26a007f3a93262334f7e416ff6c

Apple Silicon MLX only; requires strict repeat_penalty = 1.0.

Known Tradeoffs & Guardrails

  • Local-only micro-model; not hosted on api.verdictmodels.com.
  • Breaks on MLX if repeat_penalty exceeds 1.0.
Verdict 4 500M Quill (verdict-4-500m-quill) · VerdictModels