Verdict 4 35B ToolTerse v5
Canonical Cloud SKU: vc/verdict/verdict-4-35b-toolterse-v5
Weight-modified derivative of Qwen3.6-35B-A3B trained via rank-32 LoRA SFT (iter 800) across attention and GatedDeltaNet linear-attention projections to eliminate verbose docstring echoing while preserving paired BigCodeBench pass parity.
Lineage, Provenance & Runtime Specification
- Upstream Checkpoint
- Qwen/Qwen3.6-35B-A3B
- Upstream License
- Apache-2.0
- Architecture & Active Params
- qwen3_5_moe (10 Softmax + 30 GatedDeltaNet layers) · 35B total / ~3B active per token
- Certified Context / Max Output
- 32,768 tok / 8,192 tok
- Recommended Hardware Tier
- >= 32 GB Apple Silicon Unified RAM (MLX) or >= 32 GB CUDA/Vulkan (GGUF); Cloud API for < 32 GB
- Weight Modification & Audit Proof
- Gate W-GGUF verified: 100/733 tensors modified (self_attn.{q,k,v,o}_proj + linear_attn.{in_proj_qkv,out_proj} across 40 decoder layers), 633/733 tensors byte-identical to matched stock GGUF.
Measured on RunPod Serverless CA-MTL-1 (48 GB A40, llama-server GGUF Q4_K_M, 4x32K slots): warm c=1 3,872.5 tok/s prefill / 139.36 tok/s decode; c=4 254.96 tok/s decode window; FlashBoot resume TTFT 8.1-27.5s (cold new worker 43.5-63.7s).
Paired Empirical Evidence (Unmerged Comparators)
Artifact-Bound Benchmark Measurements
Token & Wall Efficiency (Comparator 1: Matched Stock GGUF)
Comparator: vs. Matched Stock Qwen3.6-35B-A3B GGUF Q4_K_M (67f8e03f…)
- Completion Tokens
- -73.15%
- Wall-Clock Time
- -70.91%
- Pass Count (BCB-100)
- 54 -> 58
Median paired delta, CI95 [-75.22%, -70.82%], p = 3.55e-15 (49 matched-PASS tasks, 3x3 order-balanced)
Median paired delta, CI95 [-73.06%, -69.39%], p = 3.55e-15
49 both pass, b=5 stock-only, c=9 v5-only (63 distinct union passes on first-100); exact McNemar p = 0.4240 — no statistically significant difference detected (not a score win)
Methodology & Caveat: Fused MLX 4-bit sibling measured separately on its own MLX stock control reads -73.29% tokens / -66.78% wall (52 -> 59, gained 12 / lost 5, p = 0.1435). Never merge comparators or lanes.
Paired Tool-Use Census (Comparator 2: Predecessor terse-v3)
Comparator: vs. Shipped Predecessor verdict-4-35b-terse-v3 GGUF Q4_K_M
- 132-Case Tool Census
- 89/132 -> 116/132
- Against Stock Qwen3.6
- 114/132 -> 116/132
+30.3% over terse-v3 (gained 39 / lost 12, exact McNemar p = 1.98e-4); MLX lane reproduces direction (b=15, c=39, p = 0.0015)
Aggregate parity vs. stock on GGUF (MLX lane: b=14, c=19, p = 0.4869) concealing a stratum split: better abstention on underspecified us_ (p = 0.00024 GGUF) vs. more no_call stalls on determined ds_ (p = 0.00342 GGUF)
Methodology & Caveat: Never claim tool-use superiority over stock Qwen3.6-35B-A3B. Pair with Verdict Proof Mode or Verdict Decision verification when unattended determined tool calls are required.
VDev Direct Agentic Coding Qualification
Comparator: VDev Direct Harness (reasoning=off)
- BCB Complete Direct
- 90.0%
- Warehouse Overall
- 56.3%
0 reasoning tokens, sub-10s median execution
N = 2,717 evaluated tasks across local/LAN warehouse
Methodology & Caveat: Measured on the Apple Silicon MLX 4-bit build, not re-measured on the Cloud RunPod CUDA GGUF Q4_K_M endpoint.
Live Basis P2 Burn & Effective Customer Rate Across Credit Packs
Hydrated live from customer_price_book.v1: raw 1:1 wallet burn is 218.78 cr/MTok input ($0.22 raw) and 6,079.448 cr/MTok output ($6.08 raw).
| Credit Pack | Pack Price / Credits | Effective $/Credit | Customer Input $/MTok | Customer Output $/MTok | 3:1:1 Blended $/MTok |
|---|---|---|---|---|---|
| Verdict Starter Pack | $5 · 2,000 cr | $0.0025 | $0.55 | $15.20 | $8.01 |
| Verdict Plus PackReference 2.0x | $10 · 5,000 cr | $0.0020 | $0.44 | $12.16 | $6.41 |
| Verdict Ultra Pack | $20 · 11,000 cr | $0.0018 | $0.40 | $11.05 | $5.83 |
| Verdict Mega Pack | $50 · 30,000 cr | $0.0017 | $0.36 | $10.13 | $5.34 |
| Verdict Pro PackMost Popular | $100 · 62,000 cr | $0.0016 | $0.35 | $9.81 | $5.17 |
| Verdict Titan PackBest Rate | $200 · 128,000 cr | $0.0016 | $0.34 | $9.50 | $5.01 |
Certified Sampler Contract (§6.2)
Engine Presets & Cryptographic Checksums
- LM Studio ignores GGUF-embedded sampler metadata and defaults to temperature=0.8, repeatPenalty=1.1; install model.yaml to enforce repeat_penalty=1.0.
- LM Studio's native MLX chat UI ignores reasoning=off levers; for local MLX use Verdict Local Gateway's offline-render lane or run GGUF via llama-server.
- Cloud Option B enforces 32,768 tokens per request slot (HTTP 400 exceed_context_size_error above 32K).
llama.cpp (llama-server)
llama-server \
-m v435btoolterse_v5_iter800_q4_k_m.gguf \
--ctx-size 32768 \
--temp 0.2 \
--repeat-penalty 1.0 \
--reasoning-budget 0 \
--jinja \
--port 8080LM Studio (model.yaml)
# Install at ~/.lmstudio/hub/models/verdict/verdict-4-35b-toolterse-v5/model.yaml
model: verdict/verdict-4-35b-toolterse-v5
base: verdict/verdict-4-35b-toolterse-v5-gguf-q4-k-m/v435btoolterse_v5_iter800_q4_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: [qwen3_5_moe]
compatibilityTypes: [gguf]
paramsStrings: [35B-A3B]
contextLengths: [32768]
reasoning: false
vision: false
trainedForToolUse: true
Verified Local Artifact Checksums
Binary Weights Staged — Gated on Phase 0b Ed25519 SigningSHA-256: 7c24da34472201afb21152cd74aca4ed0131c0a2ecb22c6b8e6aae72a32a4530
Post-normfix canonical digest only (v435btoolterse_v5_iter800_q4_k_m.gguf). Reject any pre-normfix digest.
- model-00001-of-00004.safetensors (5,343,699,404 B): f750b39e39025b5defebbf4489d939b885db967b2c256921e9cbb4efeb622f2b
- model-00002-of-00004.safetensors (5,368,472,723 B): 4d9b5f35536938af11ee070ea4c9c10248750e10765c8780d5afe4d9e2a1206a
- model-00003-of-00004.safetensors (5,368,324,201 B): b91b6f5c7e4c5f81d8690f0e7eff195c7deb6e73c25a274094209462880c0000
- model-00004-of-00004.safetensors (3,428,527,593 B): 2d6fbb09305a3727308d93a0ffc8478725faa55f668a5fddc18ca2b4abbe2d37
Per-shard digests verified; safetensors-shard-set-v1 weight_set_sha256 pending computation prior to Phase 0b publication.
Known Tradeoffs & Guardrails
- Loses 5 tasks on BCB-100 that stock Qwen3.6-35B-A3B solves (b=5, c=9); designed for worker tiers backed by test/proof verification.
- Trades terse-v3's tool over-calling for occasional no_call abstention on fully determined tool requests (ds_ stratum).
- Hard 32,768-token per-request context limit on Cloud Option B; configure Aider/OpenCode chat-history compaction accordingly.
Call vc/verdict/verdict-4-35b-toolterse-v5 via Direct API
import os, uuid
from openai import OpenAI
client = OpenAI(
base_url="https://api.verdictmodels.com/v1",
api_key=os.environ["VERDICT_API_KEY"], # vrd_live_* with literal "llm:chat" scope
timeout=160.0,
)
stream = client.chat.completions.create(
model="vc/verdict/verdict-4-35b-toolterse-v5",
temperature=0.2,
stream=True,
stream_options={"include_usage": True},
extra_headers={"Idempotency-Key": str(uuid.uuid4())},
messages=[
{"role": "user", "content": "Write a concise Python binary_search(nums, target) function."}
],
)
for chunk in stream:
if chunk.choices and chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.verdictmodels.com/v1",
apiKey: process.env.VERDICT_API_KEY, // vrd_live_* with literal "llm:chat" scope
timeout: 160_000,
});
const completion = await client.chat.completions.create(
{
model: "vc/verdict/verdict-4-35b-toolterse-v5",
temperature: 0.2,
messages: [
{ role: "user", content: "Return a TypeScript LRU cache class with get/set in minimal lines." },
],
},
{ headers: { "Idempotency-Key": crypto.randomUUID() } },
);
console.log(completion.choices[0]?.message.content);export OPENAI_API_BASE="https://api.verdictmodels.com/v1"
export OPENAI_API_KEY="$VERDICT_API_KEY" # vrd_live_* with "llm:chat" scope
# Certified 32,768-token context slot; temperature=0.2
aider \
--model "openai/vc/verdict/verdict-4-35b-toolterse-v5" \
--no-show-model-warnings \
--chat-history-tokens 8192{
"$schema": "https://opencode.ai/config.json",
"provider": {
"verdictmodels": {
"npm": "@ai-sdk/openai-compatible",
"name": "VerdictModels Direct API",
"options": {
"baseURL": "https://api.verdictmodels.com/v1",
"apiKey": "{env:VERDICT_API_KEY}"
},
"models": {
"vc/verdict/verdict-4-35b-toolterse-v5": {
"name": "vc/verdict/verdict-4-35b-toolterse-v5",
"limit": { "context": 32768, "output": 8192 }
}
}
}
}
}curl -sS https://api.verdictmodels.com/v1/chat/completions \
-H "Authorization: Bearer $VERDICT_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen | tr '[:upper:]' '[:lower:]')" \
--max-time 180 \
-d '{
"model": "vc/verdict/verdict-4-35b-toolterse-v5",
"temperature": 0.2,
"messages": [
{"role": "user", "content": "Implement parse_duration_ms(s: str) -> int in Python."}
]
}'# Cloud Direct SKU (shared Verdict Cloud wallet):
verdict-code run --model "vc/verdict/verdict-4-35b-toolterse-v5" "Refactor parser edge cases and run pytest"
# Or pair with Verdict Proof Mode for checked execution:
verdict-code run --proof --model "vc/verdict/verdict-4-35b-toolterse-v5" "Add idempotency key validation tests"