LM/Qwen 3.8 27B

llama.cpp

• https://unsloth.ai/docs/basics/dynamic-3.0-ggufs

Running

./llama.cpp/sycl/bin/llama-server \
  -hf unsloth/Qwen3.8-27B-GGUF:UD-Q6_K_M \
  --spec-type draft-mtp --spec-draft-n-max 2 -ngld 99 \
  -c 64000 -ctk q8_0 -ctv q8_0 \
  -fa on -ngl 99 --load-mode mlock -np 1 --jinja --reasoning-preserve -t 8

Benchmarking

./llama.cpp/sycl/bin/llama-bench \
  -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL \
  -ctk q8_0 -ctv q8_0 -fa on -ngl 99 \
  -p 512,1024 -n 512

./llama.cpp/sycl/bin/llama-bench \
  -hf unsloth/Qwen3.8-27B-GGUF:UD-Q5_K_XL \
  -ctk q8_0 -ctv q8_0 -fa on -ngl 99 \
  -p 512,1024 -n 512

./llama.cpp/sycl/bin/llama-bench \
  -hf unsloth/Qwen3.8-27B-GGUF:UD-Q6_K_XL \
  -ctk q8_0 -ctv q8_0 -fa on -ngl 99 \
  -p 512,1024 -n 512

$ ./llama.cpp/sycl/bin/llama-bench   -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL   -ctk q8_0 -ctv q8_0 -fa on -ngl 99   -p 512,1024 -n 512
| model                          |       size |     params | backend    | ngl | type_k | type_v |  fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -----: | -----: | --: | --------------: | -------------------: |
| qwen35 27B Q4_K - Small        |  16.68 GiB |    27.32 B | SYCL       |  99 |   q8_0 |   q8_0 |   1 |           pp512 |        769.54 ± 4.22 |
| qwen35 27B Q4_K - Small        |  16.68 GiB |    27.32 B | SYCL       |  99 |   q8_0 |   q8_0 |   1 |          pp1024 |        777.55 ± 1.27 |
| qwen35 27B Q4_K - Small        |  16.68 GiB |    27.32 B | SYCL       |  99 |   q8_0 |   q8_0 |   1 |           tg512 |         21.06 ± 0.00 |

build: 8e7f22b67 (10398)

$ ./llama.cpp/sycl/bin/llama-bench   -hf unsloth/Qwen3.8-27B-GGUF:UD-Q5_K_XL   -ctk q8_0 -ctv q8_0 -fa on -ngl 99   -p 512,1024 -n 512
| model                          |       size |     params | backend    | ngl | type_k | type_v |  fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -----: | -----: | --: | --------------: | -------------------: |
| qwen35 27B Q4_K - Small        |  18.82 GiB |    27.32 B | SYCL       |  99 |   q8_0 |   q8_0 |   1 |           pp512 |        891.35 ± 1.42 |
| qwen35 27B Q4_K - Small        |  18.82 GiB |    27.32 B | SYCL       |  99 |   q8_0 |   q8_0 |   1 |          pp1024 |        885.81 ± 0.79 |
| qwen35 27B Q4_K - Small        |  18.82 GiB |    27.32 B | SYCL       |  99 |   q8_0 |   q8_0 |   1 |           tg512 |         21.98 ± 0.03 |

build: 8e7f22b67 (10398)
$ ./llama.cpp/sycl/bin/llama-bench   -hf unsloth/Qwen3.8-27B-GGUF:UD-Q6_K_XL   -ctk q8_0 -ctv q8_0 -fa on -ngl 99   -p 512,1024 -n 512
| model                          |       size |     params | backend    | ngl | type_k | type_v |  fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -----: | -----: | --: | --------------: | -------------------: |
| qwen35 27B Q4_K - Small        |  24.13 GiB |    27.32 B | SYCL       |  99 |   q8_0 |   q8_0 |   1 |           pp512 |        806.99 ± 6.07 |
| qwen35 27B Q4_K - Small        |  24.13 GiB |    27.32 B | SYCL       |  99 |   q8_0 |   q8_0 |   1 |          pp1024 |        841.24 ± 3.10 |
| qwen35 27B Q4_K - Small        |  24.13 GiB |    27.32 B | SYCL       |  99 |   q8_0 |   q8_0 |   1 |           tg512 |         17.24 ± 0.02 |

build: 8e7f22b67 (10398)

Experiment

hf models ls --search "Qwen3.8-27B" --apps llama.cpp --expand "downloads,likes,lastModified" --sort downloads --no-truncate --limit 10

hf models ls --tree -R -h unsloth/Qwen3.8-27B-GGUF

# --mtp --mmproj-auto seem useless
./llama download --mtp --mmproj-auto -hf unsloth/Qwen3.8-27B-GGUF:UD-Q5_K_XL

hf download unsloth/Qwen3.8-27B-GGUF --include "*UD-Q4_K_XL*"
hf download unsloth/Qwen3.8-27B-GGUF --include "*UD-Q5_K_XL*"
hf download unsloth/Qwen3.8-27B-GGUF --include "*UD-Q6_K_M*"
hf download unsloth/Qwen3.8-27B-GGUF --include "mmproj-BF16*"
hf download unsloth/Qwen3.8-27B-GGUF --include "*mtp-Qwen3.8-27B-Q4_0.gguf"

tree -h ~/.cache/huggingface/hub/models--unsloth--Qwen3.8-27B-GGUF

Accuracy

https://unsloth.ai/docs/~gitbook/image?url=https%3A%2F%2F3215535692-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FxhOjnexMCB3dmuQFQ2Zq%252Fuploads%252Fl9piThTmmUsePst5w3F2%252Fimage.png%3Falt%3Dmedia%26token%3D821e88e2-ad4e-40bf-adf2-e13837228e82&width=768&dpr=3&quality=100&sign=dd5f7cb5&sv=2