/evaluations/granite-4.2-8b
Granite 4.2 8B
Published evaluation evidence and testing history. Results remain attributed to their original configurations and methods.
latest evidence 2026-09-24
Overview
IBM (ibm-granite) · 1 tested configuration · 1 evidence event · newest evidence 2026-09-24.
Contents: Findings · Event results · Tested configurations · Chronology · Technical provenance
Findings
Each finding is attributed to the event and tested configuration that measured it; exact values, failures and limitations are in the event results. A historical event's recorded status describes that event's own sections at its date and is not a verdict on newer sections.
- Model classification: NOT_READY - attributed to the 2026-09-24 event, configuration llama.cpp official Q4_K_M (reasoning-on, deployment sampler, 32K) · llama.cpp b10999 · RTX 5070.
- Recommended configuration: llama.cpp official Q4_K_M (reasoning-on, deployment sampler, 32K) (current): event result.
- Latest evidence: 2026-09-24: event result
- 2026-09-24 · llama.cpp official Q4_K_M (reasoning-on, deployment sampler, 32K) · llama.cpp b10999 · RTX 5070: classification NOT_READY. Event result
Event results
Newest first. Each event is one independent testing/publication event with its full report linked once at the top of its section; scores, failures and limitations stay visible and raw section-provenance JSON stays collapsed.
2026-09-24: First published evaluation via linked completion of the methodology-repair predecessor (official Q4_K_M, upstream llama.cpp b10999)
WELP Initial Evaluation: IBM Granite 4.2 8B (reasoning-on) · config llama.cpp official Q4_K_M (reasoning-on, deployment sampler, 32K) · llama.cpp b10999 · RTX 5070 · maturity: CURRENT_WELP · status: NOT_READY
Methodology snapshot: welp-next-snapshot-2026-09-24-context-outcome-repair · WELP commit ead28bde1ea9bce20cec6b3930125016068a8bbc
Configuration: llama.cpp official Q4_K_M (reasoning-on, deployment sampler, 32K).
WELP outcome
- Outcome: COMPLETE_PASS
- Classification: not recorded
Publication state: published; canonical evidence linked above
Quality and capabilities
- Constrained result: not recorded
Guardrails and limitations
Reliability: not recorded
LocalMaxxing
- Status: SUBMITTED
- Submission reference: not recorded
- verifiedRun: null (not claimed)
SUBMITTED/NEW, service record cmug9qe0i0d5wlq01lep45uua (APPROVED, verifiedRun false)
Tested condition: llama.cpp b10999 · RTX 5070.
Full tested identity, runtime and context details (exact hashes, versions and configuration)
Identity
| Field | Value |
|---|---|
| Profile identity | granite-4.2-8b-q4-k-m-llamacpp-b10999-rtx5070-deployment |
| Model | Granite 4.2 8B |
| Producer | not recorded |
| Tested artifact | not recorded |
| Precision | not recorded |
| Artifact SHA-256 | 16a9369d0805f80b7377d25d87f937a90c05dc04ad79173a52001e42c9aab311 |
| Campaign | granite-4.2-8b-rtx5070-welp-context-outcome-completion-2026-09-24 |
| Record date | 2026-09-24 |
Runtime and hardware
| Field | Value |
|---|---|
| Engine | llama.cpp b10999 |
| Runtime tag | b10999 |
| Runtime commit | b04d4e567cd2fb8d2ded6e17d38dbbcfafe29063 |
| Runtime build | build-cuda-sm120 |
| Hardware | NVIDIA GeForce RTX 5070 12 GB |
Context profile
| Field | Value |
|---|---|
| Practical default | not recorded |
| Guarded context | not recorded |
| Native model-card maximum | not recorded |
| Model-card envelope complete | not recorded |
| Native maximum disposition | not recorded |
Tested configurations
Exact profile identities, sampling conditions and provenance are in each configuration's details below.
| Configuration | Artifact / precision | Runtime | Hardware | Context / reasoning | Events |
|---|---|---|---|---|---|
| llama.cpp official Q4_K_M (reasoning-on, deployment sampler, 32K) · llama.cpp b10999 · RTX 5070 | Q4_K_M official publisher GGUF | llama.cpp b10999 | RTX 5070 | not recorded | 1 (2026-09-24) |
Configuration details: llama.cpp official Q4_K_M (reasoning-on, deployment sampler, 32K) · llama.cpp b10999 · RTX 5070
- Full profile name: llama.cpp official Q4_K_M (reasoning-on, deployment sampler, 32K).
- Profile identity:
granite-4.2-8b-q4-k-m-llamacpp-b10999-rtx5070-deployment. - Status: current canonical/recommended tested surface.
- Deployment topology (as recorded): Full-GPU upstream llama.cpp CUDA serving on RTX 5070 12GB: -ngl 99 (40/40 layers), -fa on, f16 KV, -np 1, embedded GGUF Jinja template, DEPLOYMENT sampler (temp 0.2 / top_k 80 / top_p 1.0 / repeat_penalty 1.05); effective reasoning ON (built-in thinking; OFF control proven effective but not the campaign profile). Default context 32,768 / native exact 131,072; uncached scientific arms via --cache-ram 0 --no-cache-prompt --slot-prompt-similarity 0 with cache_prompt:false (proven by repeated-prompt probe). Publisher sampler (temp 1.0 / top_p 0.95) measured as a matched comparison, never pooled.
- Artifact (as recorded): ibm-granite/granite-4.2-8b-GGUF@93f3f6a8 :: granite-4.2-8b-Q4_K_M.gguf (sha256 16a9369d0805f80b7377d25d87f937a90c05dc04ad79173a52001e42c9aab311)
- Runtime (as recorded): llama.cpp b10999.
- Hardware (as recorded): NVIDIA GeForce RTX 5070 12 GB.
- Profile Metadata
Events on this configuration:
Chronology
Compact index; full results are in Event results.
| Date | Event | Configuration | Status |
|---|---|---|---|
| 2026-09-24 | First published evaluation via linked completion of the methodology-repair predecessor (official Q4_K_M, upstream llama.cpp b10999) | llama.cpp official Q4_K_M (reasoning-on, deployment sampler, 32K) · llama.cpp b10999 · RTX 5070 | NOT_READY |
Technical provenance
Publication, acceptance and source-pin provenance for each event, collapsed; the scientific content above never depends on it.
Event provenance: 2026-09-24 WELP Initial Evaluation: IBM Granite 4.2 8B (reasoning-on)
- Campaign:
granite-4.2-8b-rtx5070-welp-context-outcome-completion-2026-09-24 - Export disposition: WEBSITE_PUBLISHED; publication date 2026-09-24
- Canonical citation (immutable commit/path pin):
https://github.com/WumboLabs/evaluations/blob/adcfa178b6dd9b52eede2c433ffc691dbcd26941/models/granite-4.2-8b/events/granite-42-8b-rtx5070-welp-context-completion-20260924/REPORT.md - Export identity: event_date
2026-09-24, event_idgranite-42-8b-rtx5070-welp-context-completion-20260924, event_typeinitial-evaluation, model_idgranite-4.2-8b, predecessor_campaigngranite-4.2-8b-rtx5070-welp-characterization-2026-09-24, profile_idgranite-4.2-8b-q4-k-m-llamacpp-b10999-rtx5070-deployment, profile_statuscurrent - Export source pin: repository-cache WumboLabs/evaluations @
250afdf042677d8c6dc19275c357ad0f5a2b870apath models/granite-4.2-8b/events/granite-42-8b-rtx5070-welp-context-completion-20260924/website-publication.json sha256978d09e20e166ff7ecec559a1b10a5a7d3de10292aa663ac3e6ce6e018cced1b
Publication provenance note (as recorded): Native current-WELP linked completion event under the consolidated architecture. The retained COMPLETE_WITH_GAPS predecessor campaign is preserved unchanged and unpublished; every raw evidence file is reused byte-identically (size + SHA-256 verified); only the answerless context cell's disposition/outcome is re-derived from original raw bytes under welp-context 0.3.0-draft.