Qwen2.5 27B
2× RTX 3090 · llama.cpp
- throughput:
- 70.0 t/s gen · 1850.0 t/s pp
- quant:
- Q6_K_XL (gguf)
coding
Multi-token prediction enabled. 96GB total VRAM (24+24? but user says 96GB system). Reliable for code generation and codebase ingestion.
Alibaba · 3 reports
2× RTX 3090 · llama.cpp
Multi-token prediction enabled. 96GB total VRAM (24+24? but user says 96GB system). Reliable for code generation and codebase ingestion.
RTX 5090 · vLLM
Benchmark of abliteration tools (Apostate, Huihui, Heretic) on Qwen 2.5 7B. Evaluated with lm-evaluation-harness via vLLM 0.19.0, bf16 on RTX 5090 32GB. Reports MMLU, GSM8K, HellaSwag, ARC Challenge, WinoGrande, TruthfulQA MC2, PiQA, LAMBADA ppl, HarmBench ASR, KL divergence. No tokens/sec reported.
RTX 3090 · llama.cpp · 32,768 ctx
Solid for autocomplete, occasionally hallucinates imports in multi-file refactors. Build b4400.