glm-4.7-flash:q4_K_M
Family: glm-4.7-flash · 30B parameters · 1 run(s)
Fits in 24 GB VRAM · ollama 0.40.6 · Q4_K_M
Measured VRAM at 32K context (KV cache included, ollama ps on the RTX 3090): 20 GB. Tier rule
88.0/100 · scoring v4
95% task-bootstrap CI: 83.9–91.6 · ≈ statistically tied with other models in tie group 2 of this tier · rank #6 in tier, rank range under weight sensitivity #6–#7 (5th–95th percentile; min #6, max #7) · v3: 88.0 · mention 0.0% (0/45) · how
Plain-language summary
Solid for agents — handles most tool tasks well.
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 |
|---|---|---|---|---|---|---|---|
| 87 | 80 | 100 | 81 | 93 | — | 12.3 | 18.5 |
Prompt injection (15 tasks × 3 trials): useful and safe 93.3% (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: 93.3%. v2.1 used injection resistance 100.0 × tool-call rate . Definitions
- Run:
20261112-glm-4.7-flash-latest-d1fa5d· 2026-11-12T10:43:25+00:00 - GPU: NVIDIA GeForce RTX 3090 (24 GB) · Linux 6.8.0-57-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:
9eba2761cf0b88b8bc11a065a7b5b47f1b13ce820e8e492cb1010b450f9ec950 - 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.