Llama 2 70b KronQ W3A16 Fake by donghyunli — 68.98B open-weight local LLM. License: llama2. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopllm.com.
Key specs
| Type | Local open-weight |
|---|
| Parameters | 68.98B total |
|---|
| Architecture | llama |
|---|
| Context window | 4K tokens |
|---|
| Knowledge cutoff | — |
|---|
| Modalities | text |
|---|
| Recommended backends | — |
|---|
| Minimum viable rig | — |
|---|
Benchmark scores
| GPQA Diamond | — |
|---|
| SWE-bench Verified | — |
|---|
| AIME | — |
|---|
| MMLU-Pro | — |
|---|
| BFCL v3 (tool use) | — |
|---|
| Composite score | — |
|---|
| Community rating | No reviews yet |
|---|
VRAM & disk per quantization
| Quant | VRAM | Disk | RAM | Context |
|---|
| Q4_K_M | 41.5 GB | 40 GB | — | 4K |