Qwen3.6-35B-A3B-MTP-Q2_K_XL Hermes Benchmark Failure Report

Result: Failed by user request due to speed

This run was stopped because the model was too slow for the benchmark. LM Studio moved from prompt processing into generation, but Hermes still had no usable response, no tool call, and no benchmark progress after 172.3 seconds waiting on the model response.

Model label

Qwen3.6-35B-A3B-MTP-Q2_K_XL

LM Studio identifier

qwen3.6-35b-a3b-mtp@q2_k_xl

Hermes displayed model

qwen3.6-35b-a3b-mtp@q2_k_xl

Quantization noted by user

Q2_K_XL

Reasoning effort

high

LM Studio context

150,000 tokens

LM Studio size / parallel / device

14.36 GB / 4 / MGPC

Hermes session key

20260527_070908_4d89ba

Hermes session duration

3m 16s

API endpoint

http://127.0.0.1:1234/v1

Run Summary

Checkpoint	Status	Evidence
Confirm loaded model	Passed	LM Studio showed `qwen3.6-35b-a3b-mtp@q2_k_xl` loaded and idle with a `150000` token context. Hermes displayed the same model in the session header.
Set reasoning high	Passed	Hermes confirmed `Reasoning effort set to 'high' (saved to config)`.
Submit benchmark prompt	Passed	The prompt instructed Hermes to use `Qwen3.6-35B-A3B-MTP-Q2_K_XL`, read `/Users/armanshawon/Documents/Benchmark/test-prompt.md`, and create the required result file in the Benchmark folder.
Prompt processing	Slow	LM Studio entered `PROCESSINGPROMPT` while Hermes showed `0/150K`.
Generation	Too slow	LM Studio moved to `GENERATING`, but Hermes still had no response or tool call after `172.3s` waiting on the model response.
Read `test-prompt.md`	Not reached	Hermes exited with `0 tool calls`; no file-read tool was called.
Create benchmark HTML	Not reached	No benchmark artifact was written by the tested model.

Timing

Metric	Observed value
Hermes session duration	3m 16s
Interrupted API wait	172.3s elapsed waiting for model response
Hermes context display	0/150K, 0%
Tool calls completed	0
Benchmark progress	No prompt file read; no task work started

Interruption Details

Hermes message: Operation interrupted: waiting for model response (172.3s elapsed).
LM Studio status during run: PROCESSINGPROMPT, then GENERATING.
Post-stop LM Studio status: no models loaded.
Hermes final summary: 1 user message, 0 tool calls.

Timeline

Time	Event
2026-05-27 07:09:08 +0600	Fresh Hermes session opened. Session key: `20260527_070908_4d89ba`.
Start of run	LM Studio confirmed `qwen3.6-35b-a3b-mtp@q2_k_xl`, size `14.36 GB`, context `150000`, parallel `4`, device `MGPC`.
Before benchmark prompt	Hermes confirmed `/reasoning high`.
Early run	LM Studio showed `PROCESSINGPROMPT`; Hermes showed `0/150K`.
Mid run	LM Studio switched to `GENERATING`, but Hermes still had no visible model response or tool calls.
Fail decision	User requested failure for speed; Hermes API call was interrupted at `172.3s`.
End of run	Hermes session exited after `3m 16s` with `1` user message and `0` tool calls.

Tool Call Detail

Tool or command	Purpose	Result
`hermes`	Started a fresh Hermes CLI session.	Succeeded; model header showed `qwen3.6-35b-a3b-mtp@q2_k_xl`.
`/reasoning high`	Set Hermes reasoning effort to high before the test prompt.	Succeeded; Hermes saved the setting.
Benchmark prompt	Requested the model-specific benchmark and asked Hermes to read `test-prompt.md`.	The model did not return a usable response before the run was failed for speed.
Hermes model tool calls	Expected file read and result-file creation actions.	None occurred. Hermes summary showed `0 tool calls`.

Judgment

Fail this run as too slow for the Hermes benchmark on this machine. Although the model reached generation, it did not produce the first actionable response or tool call before the user-requested cutoff.