Hardware › A10 local LLM benchmarks: 8 measured configs
A10 local LLM benchmarks: 8 measured configs
8 measured local-LLM configs on NVIDIA A10 (24GB); fastest 14B+ model Qwen3.5-35B-A3B at 97.9 tok/s. Official specs, every number linked to its source.
Snapshot 2026-10-15 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
Quick answers
- What is the fastest model on A10?
- Qwen3.5-35B-A3B at 97.9 tok/s single-stream (Q4_K_M, llama.cpp/cuda), source last checked 2026-10-14. Models under 14B parameters are left out of this answer. source
- How many configs does TokenMark track for A10?
- 8 single-stream configs across 5 models, each linked to the README or model card it came from.
Measured single-stream configs on NVIDIA A10 (24GB)
| Model | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|
| Qwen3.5-35B-A3B | Q4_K_M | llama.cpp/cuda | 97.9 tok/s | 8192 | Verified (ran it) | source |
| Qwen3.6-35B-A3B | UD-Q4_K_M | llama.cpp/cuda | 95.4 tok/s | 8192 | Verified (ran it) | source |
| Qwen3.6-35B-A3B | UD-Q4_K_XL | llama.cpp/cuda | 91.3 tok/s | 8192 | Verified (ran it) | source |
| Qwen3.8-27B | INT4 | vllm | 28.4 tok/s (prefill 1111.3) | 32768 | Verified (ran it) | source |
| Qwen3.8-27B | UD-Q4_K_M | llama.cpp/cuda | 24.9 tok/s | 8192 | Verified (ran it) | source |
| Qwen3.6-27B | Q4_K_M | llama.cpp/cuda | 24.1 tok/s | 8192 | Verified (ran it) | source |
| Qwen3.5-27B | Q4_K_M | llama.cpp/cuda | 23.5 tok/s | 8192 | Verified (ran it) | source |
| Qwen3.8-27B | UD-Q4_K_XL | llama.cpp/cuda | 23.5 tok/s | 8192 | Verified (ran it) | source |
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.