gemma 4 31B it uncensored
Fine-tune of Gemma 4 31B IT
composite n/acompare to base
fine-tune not yet benchmarked
Measured axis deltas appear after both rows have board data.
Gemma 4 31B IT
Fine-tune of google/gemma-4-31B
Every measured variant of this model: how much quality each quant keeps, and the VRAM and speed it costs to run.
VRAM footprint vs Local Intelligence Index
LB-2026-07.2 | 25/22.5/22.5/22.5/7.5. Where this model and current-lane family runs land vs the frontier anchors.
Swipe horizontally to inspect the full chart →
This modelDashed vertical lines mark common VRAM tiers.Amber points are synthetic demo preview data.
Variant profiles
Complete rows are ordered by Local Intelligence Index; partial rows show their measured axes but are not ranked. The VRAM/Fits columns (8Kcontext) tell you what your card needs. Ranks are within this family's variants.
Column guide
Variant — quant label plus, where sha-verified, the publisher of the exact weights file benchmarked; rows without a source line predate artifact identity records.
VRAM @8k — model weights, KV cache, and runtime headroom at 8k context.
Fits — the smallest common GPU VRAM tier above that estimate.
Prefill tok/s — prompt-processing speed.
Decode tok/s — generated-token speed after the prompt.
Overall tok/s — completion throughput across the full benchmark.
File size — the benchmarked model artifact on disk.
Runtime — the serving engine and version.
Run — the immutable benchmark receipt. Live rows link to the public submission record until the run is baked into the static site.
Pick the largest quant whose VRAM @8k fits your card.
Swipe horizontally for all variant metrics →
| Rank (this family) | Variant | Local Intelligence IndexLB-2026-07.2 | 25/22.5/22.5/22.5/7.5 | Agentic | Knowledge | Instruction | Coding | Math | VRAM @8k | Fits | Prefill tok/s | Decode tok/s | Overall tok/s | File size | Runtime | Run |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Q4_K_Mbestby unsloth | 51.7±3.1 Agentic 10.4 / Knowledge 87.4 / Instruction 79.3 / Coding 35.5 / Math 48.2 | 10.4±8.5 | 87.4±3.6 | 79.3±4.8 | 35.5±7.8 | 48.2±8.6 | 20.9 GB | 24 GB | 2,425.1 | 63.1 | 48.4 | 18.3 GB | llama.cppb9852/fd1a05791 | receipt |
| — | Q8_0by unsloth | no run yet | — | — | — | — | — | 35.1 GB | 48 GB | — | 32.6 GB | — | benchmark it | ||
| — | Q6_Kby unsloth | no run yet | — | — | — | — | — | 27.8 GB | 32 GB | — | 25.2 GB | — | benchmark it | ||
| — | Q5_K_Mby unsloth | no run yet | — | — | — | — | — | 24.2 GB | 32 GB | — | 21.7 GB | — | benchmark it | ||
| — | Q3_K_Mby unsloth | no run yet | — | — | — | — | — | 17.2 GB | 24 GB | — | 14.7 GB | — | benchmark it |
vs base