Qwen3.6 27B is 27.78B, 262,144 tokens on the official card. Qwen3.8 27B is 27.8B, 262,144 tokens. Q6 / Q5 / Q4 file sizes come from the listed GGUFs on each /models page, or a calculator estimate when a listing is missing. Q3 stays off. Q4 files fit one R9700 at 4K on the calculator for both sides. Neither model was measured on the local desktop. Fit numbers are calculator estimates. llama.cpp first.
How we test — Measured cells cite official amdai-bench/run@1 cards. Estimates stay labeled. Q3 is estimate-only. Q1/Q2 stay off.
Cited, not measured on the local desktop
Dense 27B — cited, not measured
Full model page · Official card · GGUF · Can an R9700 run it? · Open in calculator
Cited, not measured on the local desktop
Dense 27B — cited, not measured
Full model page · Official card · GGUF · Can an R9700 run it? · Open in calculator
Existing GPU sheets only: R9700, RX 7900 XTX, RX 7900 XT, RX 7800 XT. llama.cpp, f16 KV. Totals are calculator estimates. Speed is measured only on R9700 35B cells that already exist; everything else stays not measured yet. This table lists Q6 / Q5 / Q4. Q3 stays on the calculator as a labeled estimate.
| Quant | Kind | Qwen3.6 27B 4K | Qwen3.6 27B 32K | Qwen3.6 27B 256K | Qwen3.8 27B 4K | Qwen3.8 27B 32K | Qwen3.8 27B 256K |
|---|---|---|---|---|---|---|---|
|
Q6
Q6_K / UD-Q6_K |
Estimate |
22.1 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
23.9 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
38.1 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.6 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
23.4 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
37.6 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
|
Q5
Q5_K_M / UD-Q5_K_M |
Estimate |
19.2 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.0 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
35.2 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
19.5 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.3 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
35.5 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
|
Q4
Q4_K_M / UD-Q4_K_M |
Estimate |
16.7 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
18.5 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
32.7 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
16.4 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
18.1 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
32.3 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
| Quant | Kind | Qwen3.6 27B 4K | Qwen3.6 27B 32K | Qwen3.6 27B 256K | Qwen3.8 27B 4K | Qwen3.8 27B 32K | Qwen3.8 27B 256K |
|---|---|---|---|---|---|---|---|
|
Q6
Q6_K / UD-Q6_K |
Estimate |
22.1 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
23.9 GB Tight — little desktop headroom not measured yet No official local desktop cell for this model × card. Not measured yet. |
38.1 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.6 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
23.4 GB Tight — little desktop headroom not measured yet No official local desktop cell for this model × card. Not measured yet. |
37.6 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
|
Q5
Q5_K_M / UD-Q5_K_M |
Estimate |
19.2 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.0 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
35.2 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
19.5 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.3 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
35.5 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
|
Q4
Q4_K_M / UD-Q4_K_M |
Estimate |
16.7 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
18.5 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
32.7 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
16.4 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
18.1 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
32.3 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
| Quant | Kind | Qwen3.6 27B 4K | Qwen3.6 27B 32K | Qwen3.6 27B 256K | Qwen3.8 27B 4K | Qwen3.8 27B 32K | Qwen3.8 27B 256K |
|---|---|---|---|---|---|---|---|
|
Q6
Q6_K / UD-Q6_K |
Estimate |
22.1 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
23.9 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
38.1 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.6 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
23.4 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
37.6 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
|
Q5
Q5_K_M / UD-Q5_K_M |
Estimate |
19.2 GB Tight — little desktop headroom not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.0 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
35.2 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
19.5 GB Tight — little desktop headroom not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.3 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
35.5 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
|
Q4
Q4_K_M / UD-Q4_K_M |
Estimate |
16.7 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
18.5 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
32.7 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
16.4 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
18.1 GB Fits in VRAM (estimate) not measured yet No official local desktop cell for this model × card. Not measured yet. |
32.3 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
| Quant | Kind | Qwen3.6 27B 4K | Qwen3.6 27B 32K | Qwen3.6 27B 256K | Qwen3.8 27B 4K | Qwen3.8 27B 32K | Qwen3.8 27B 256K |
|---|---|---|---|---|---|---|---|
|
Q6
Q6_K / UD-Q6_K |
Estimate |
22.1 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
23.9 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
38.1 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.6 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
23.4 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
37.6 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
|
Q5
Q5_K_M / UD-Q5_K_M |
Estimate |
19.2 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.0 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
35.2 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
19.5 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
21.3 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
35.5 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
|
Q4
Q4_K_M / UD-Q4_K_M |
Estimate |
16.7 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
18.5 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
32.7 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
16.4 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
18.1 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
32.3 GB Does not fit this GPU not measured yet No official local desktop cell for this model × card. Not measured yet. |
When a shopper file does not fit, the spill is system RAM. Shopper lines stay Minimum system RAM needed and RAM needed at full context on one R9700 at the model’s shopper quant, 32K selected and the official-card full context. Estimate unless a measured R9700 card overlays the kit.
Q4_K_M at 4K or 32K does not fit every listed card on the calculator.
Minimum system RAM needed
32 GB kit
Estimate · 24.7 GiB raw · 32K context
RAM needed at full context
32 GB kit
Estimate · 24.6 GiB raw · 8K full context
Estimate. Offloaded weights + KV in RAM + runtime + OS/desktop + headroom, rounded up to a 32 GB DIMM kit.
UD-Q4_K_M at 4K or 32K does not fit every listed card on the calculator.
Minimum system RAM needed
32 GB kit
Estimate · 24.7 GiB raw · 32K context
RAM needed at full context
32 GB kit
Estimate · 24.6 GiB raw · 8K full context
Estimate. Offloaded weights + KV in RAM + runtime + OS/desktop + headroom, rounded up to a 32 GB DIMM kit.
Commands and recipes already on the model pages. Cited-model shapes are not measured local desktop recipes. House Flash keeps its existing Strata recipe plus the llama.cpp backend page.
Qwen3.6 27B llama.cpp Q4_K_M llama.cpp
# Shape only — not a measured local desktop recipe. ./build-vk/bin/llama-server \ -m ~/models/Qwen3.6-27B-Q4_K_M.gguf \ -ngl 99 \ -c 8192 \ --cache-type-k f16 \ --cache-type-v f16 \ --host 127.0.0.1 --port 8080
Qwen3.8 27B llama.cpp UD-Q4_K_M llama.cpp
# Shape only — not a measured local desktop recipe. ./build-vk/bin/llama-server \ -m ~/models/Qwen3.8-27B-UD-Q4_K_M.gguf \ -ngl 99 \ -c 8192 \ --cache-type-k f16 \ --cache-type-v f16 \ --host 127.0.0.1 --port 8080
Both models hold a Q4 file on one R9700 at 4K on the calculator. Neither side has a local desktop decode cell. Pick on size, active params, and VRAM headroom, not a speed we invent.
Keep llama.cpp first. The side that holds Q4 in VRAM (Qwen3.6 27B and Qwen3.8 27B) is the less painful coding-agent host. House Flash / agent pins stay R9700 / local desktop — they do not transfer. No invented agent speed.
Cited context is 262,144 tokens vs 262,144 tokens. KV grows with context. Q4 at 32K fits Qwen3.6 27B and fits Qwen3.8 27B on one R9700. Read /long-context for measured R9700 35B 128K–262K cards. We do not invent a 128K decode figure here.
Qwen3.6 27B files: Q6_K 22.52 GB, Q5_K_M 19.51 GB, Q4_K_M 16.82 GB. Qwen3.8 27B files: UD-Q6_K 21.98 GB, UD-Q5_K_M 19.77 GB, UD-Q4_K_M 16.46 GB. Fit on the four existing GPU sheets below. Empty speed cells stay not measured yet.
Open in Stack Lab only where the handoff is already allowlisted. Doctor is always here. House daily / Flash / agent profiles appear only when that house model is on the pair.
If the app is not installed, packages are not published yet. There is no public download URL. Read the Stack Lab install notes . If Stack Lab is already running on this machine, open the local app .
Pages: Qwen3.6 27B · Qwen3.8 27B · All model compares · Compare GPUs · Compare 35B · Benchmarks · Stack Lab · Long context · Calculator