nemotron-3.5-bolt:e4b
Family: nemotron-3.5-bolt · 8B parameters · 1 run(s)
Fits in 8 GB VRAM · ollama 0.40.10 · Q4_K_M
Not comparable: ran on Ollama 0.40.10; the published series uses 0.40.6. Hermes 9cb34e9, ctx 32768, score shown for information only.
Measured VRAM at 32K context (KV cache included, ollama ps on the RTX 3090): not measured (no valid ollama ps size for this run; tier kept as published). Tier rule
92.4/100 · scoring v4
95% task-bootstrap CI: 88.6–95.9 · rank # in tier, rank range under weight sensitivity #–# (5th–95th percentile; min #, max #) · v3: 92.4 · mention 0.0% (0/45) · how
Plain-language summary
Excellent at tool-using assistant work on this suite.
Good for
- returning clean JSON
- matching the requested format
- picking the right tool
- multi-step plans
- staying safe under prompt injection
Weak at
- —
Category breakdown
| JSON | Schema | Tool | Multi-step | Injection (useful&safe) | tok/s | p50 s/task | p95 s/task |
|---|---|---|---|---|---|---|---|
| 100 | 80 | 100 | 85 | 100 | — | 12.8 | 18.4 |
Prompt injection (15 tasks × 3 trials): useful and safe 100.0% (task completed and not compromised; counts in the score) · utility under attack —% (completed the user's task) · harmful-action attack success 0.0% (a real harmful tool call or canary leak). Mentions (quoting the attacker without acting): 0.0% (0/45); they do not lower the score. v3 useful and safe: 100.0%. v2.1 used injection resistance 100.0 × tool-call rate . Definitions
- Run:
20261112-nemotron-3.5-bolt-e4b-49bb2d· 2026-11-12T19:05:30+00:00 - GPU: NVIDIA GeForce RTX 3090 (24 GB) · Linux 6.8.0-85-generic
- Host:
· kind not recorded · measured · hosts - Harness: hermes-agent Hermes Agent v0.22.2+2363.g9cb34e9 (2026.9.24) · stable · local 9cb34e9e285d · trials 3 · sampling: Ollama default (temperature and seed not set by harness) · context window: 32768 tokens as loaded by Ollama (the unused runner field records 8192; see Methodology)
- GGUF sha256:
c8af2b8aea10a690a1d9491db744a9446660173cb38fc489612b556615a69612 - Sponsor disclosure: none
Chat template vs upstream
No reference
Labels are only “matches / differs / no reference”, never safe/unsafe. Ollama may use a built-in Go template or renderer instead of the GGUF Jinja. Why templates matter: Chat-template backdoors. Not part of the score.