- Prose writing speedchat_decode_tps · tok/s
- 28.36 tok/sper person · mean · sample count not recorded
- First word afterttft_median_s · s
- 0.14 sper person · median · sample count not recorded
- Slowest first wordttft_max_s · s
- 0.29 sper person · max · sample count not recorded
- Machine totalaggregate_e2e_tps · tok/s
- 56.46 tok/smachine total · single · sample count not recorded
- Peak memory, whole hostpeak_host_unavailable_gib · GiB
- 13.37 GiBmachine total · max · sample count not recorded
Runs on this setup
Earlier runs keep their own engine versions and outcomes. Workload shapes stay separate.
History and measured sweep
| Date | Shape | Each person · median | Machine total | First word · median | Result | Run |
|---|---|---|---|---|---|---|
2026-10-09 | 2 people | not recorded | 56.46 tok/s | 0.14 s | Not graded | |
2026-10-09 | 1 people | not recorded | 28.05 tok/s | 0.13 s | Not graded | |
2026-10-09 | 1 people | not recorded | 28.05 tok/s | not recorded | Not graded | |
2026-10-09 | 2 people | not recorded | 56.46 tok/s | not recorded | Not graded |
Answer checks
6/6 request checks
Method
Code or prose speed smoke, three measured batches after one excluded warmup per user count. Returned token accounting; per-person decode and simultaneous aggregate decode are separate.
Limits
Speed only; outputs reach the token ceiling and do not establish correctness. Whole-Mac memory includes existing applications. Filled contexts observed whole-Mac swap growth; a memory-stable recipe, managed lifecycle and delivery remain unassessed.
What ran
Exact identity
- Original publisher model
- Qwen3-8B-Base
- Publisher revision
49e3418fbbbca6ecbdf9608b4d22e5a407081db4- Variant · format · precision
- Q4_K_M GGUF variant · GGUF · Q4_K_M
- Weights SHA-256
- not recorded
- Engine · version · feature
- llama.cpp Metal ·
b11182· plain - Hardware
- Apple M6 Mac mini, 16 GiB unified memory
- Harness / workload
not recorded- Workload suite · version
not recorded- Harness SHA-256
not recorded- Fixture SHA-256
not recorded
Workload shape
- People in this run
- 2
- Configured window (tokens)
- 4096
- KV cache precision
- q8_0
- Output token ceiling
- 512
- Thinking
- off
Full reproduction pack available to customers and evaluators on request
All recorded numbers
Metric definitions, scope and statistics
| Metric | Value | Scope | Statistic | Sample count | Basis / source field | Run |
|---|---|---|---|---|---|---|
ttft median s | 0.14 s | per person | median | not recorded | ttft_median_s | |
chat decode tps | 28.36 tok/s | per person | mean | not recorded | chat_decode_tps | |
ttft max s | 0.29 s | per person | max | not recorded | ttft_max_s | |
requests ok | 6.00 count | machine total | single | not recorded | requests_ok | |
aggregate concurrency | 2.00 count | machine total | single | not recorded | aggregate_concurrency | |
requests total | 6.00 count | machine total | single | not recorded | requests_total | |
aggregate e2e tps | 56.46 tok/s | machine total | single | not recorded | aggregate_tps | |
chat ttft mean s | 0.16 s | per person | mean | not recorded | chat_ttft_mean_s | |
peak host unavailable gib | 13.37 GiB | machine total | max | not recorded | peak_host_unavailable_gib |
Data and citation
Skilak Keep evidence, run 136c3c4112ce4092b34f7835, measured 2026-10-09T20:03:41.006639+00:00. https://skilak.ai/keep/resources/evidence/r/136c3c4112ce4092b34f7835
