Use 4 GiB tier (1 GiB arena) in v1/v2 examples

README.md

@@ -34,35 +34,37 @@ hf download unsloth/flint-GGUF flint-UD-Q4_K_XL.gguf --local-dir models
 
 ## Run
 
-Prompt used below: `Explain in one sentence why the sky is blue.`
+Examples use the 4 GiB memory tier (`SDQ_ARENA_MB=1024`, a 1 GiB expert arena). Prompt: `Explain in one sentence why the sky is blue.`
 
-**native** (unmodified llama.cpp MoE path, needs about 24 GiB RAM):
+**native** (unmodified llama.cpp MoE path, needs about 24 GiB RAM, so it does not fit in 4 GiB):
 
 ```bash
 SDQ_PAGER=0 build/bin/llama-cli -m models/flint-UD-Q4_K_XL.gguf -c 512 \
   -p 'Explain in one sentence why the sky is blue.' -n 32 -t 16 --temp 0 -st --simple-io
 ```
 
-**v1** (expert paging, mode C). Preload and row-parallel default to on, so turn them off explicitly. `SDQ_ARENA_MB` is the expert cache size in MiB:
+**v1** (expert paging, mode C). Preload and row-parallel default to on, so turn them off explicitly:
 
 ```bash
-SDQ_PAGER=1 SDQ_ARENA_MB=18432 SDQ_PRELOAD=0 SDQ_ROW_PARALLEL=0 \
+SDQ_PAGER=1 SDQ_ARENA_MB=1024 SDQ_PRELOAD=0 SDQ_ROW_PARALLEL=0 \
   build/bin/llama-cli -m models/flint-UD-Q4_K_XL.gguf -c 512 \
   -p 'Explain in one sentence why the sky is blue.' -n 32 -t 16 --temp 0 -st --simple-io
 ```
 
-**v2** (default settings: preload and row-parallel on). The arena must hold all 12,032 experts, so use at least 28.6 GiB:
+**v2** (default settings, preload and row-parallel on). At 4 GiB the arena cannot hold all experts, so v2 runs the same path as v1 here:
 
 ```bash
-SDQ_PAGER=1 SDQ_ARENA_MB=29400 \
+SDQ_PAGER=1 SDQ_ARENA_MB=1024 \
   build/bin/llama-cli -m models/flint-UD-Q4_K_XL.gguf -c 512 \
   -p 'Explain in one sentence why the sky is blue.' -n 32 -t 16 --temp 0 -st --simple-io
 ```
 
+v2 changes behavior only when the arena holds all 12,032 experts (≥ 28.6 GiB, for example `SDQ_ARENA_MB=29400`).
+
 Use 16 threads (`-t 16`). Row-parallel needs more threads than the number of experts used per step (6), so at least 7.
 
 ## Notes
 
-- Memory: the process needs about 1.8 GiB plus the arena. Under a 2 GiB limit a 128 MiB arena works (peak 1.89 GiB); 256 MiB does not.
-- Speed (32 GiB, 16 threads): native 19.4 t/s generation, v1 5.5 t/s, v2 13.7 t/s. Details and memory-tier tables are in the report.
+- Memory at 4 GiB tier: peak 2.76 GiB. The process needs about 1.8 GiB plus the arena. Under a 2 GiB limit a 128 MiB arena works (peak 1.89 GiB); 256 MiB does not.
+- Generation speed, 4 GiB tier, 16 threads (median): v1 4.6 t/s, v2 4.6 t/s (same path). At 32 GiB with full arena: native 19.4 t/s, v1 5.5 t/s, v2 13.7 t/s. Details are in the report.
 - Output matches native greedy decoding at 8 threads; at 16 threads it diverges after a few tokens (float reordering). See the report.