Qwen3.6-35B is 35B total / 3B active, 262,144 tokens on the official card. Qwen 3.8 Flash is 125B total / 6B active, 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 fits Qwen3.6-35B on one R9700 at 4K and spills on Qwen 3.8 Flash. Qwen3.6-35B has measured llama.cpp cells on the local desktop. Qwen 3.8 Flash speed is not measured yet. 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.
Official card: 35B total / 3B active, 40 layers, 10 full-attention (GQA 2×256). Only those 10 layers grow a token-length KV cache. The other 30 hold a fixed linear-attention state.
Official card (Qwen3.8-Flash-Next): 125B total / 6B active, plus a 51B n-gram embedding llama.cpp can keep in system RAM. 48 layers, 12 sparse-attention layers (GQA 2×256) plus a 12×256 indexer cache (raw + pooled key). 36 linear layers hold a fixed state. Publisher UD-Q6_K_XL folder lists ~169 GB.
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.
No official local desktop cell for this model × card. Not measured yet.
28.2 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.
160.4 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
161.2 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
167.9 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
Q5
UD-Q5_K_XL / UD-Q5_K_XL
Estimate
25.7 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
26.2 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
30.7 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
150.3 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
151.1 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
157.8 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_XL
Estimate
20.6 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
21.2 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
25.6 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
105.6 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
106.4 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
113.1 GB
Does not fit this GPU
not measured yet
No official local desktop cell for this model × card. Not measured yet.
System RAM
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.
Qwen3.6-35B
UD-Q5_K_XL at 4K or 32K does not fit every listed card on the calculator.
Minimum system RAM needed
32 GB kit
Estimate · 24.8 GiB raw · 32K context
RAM needed at full context
32 GB kit
Estimate · 24.8 GiB raw · 256K full context
Estimate. Offloaded weights + KV in RAM + runtime + OS/desktop + headroom, rounded up to a 32 GB DIMM kit.
Breakdown
Offloaded weights ·
0 GiB
Separable embed in RAM ·
0 GiB
KV in RAM at selected ·
0 GiB
KV in RAM at full context ·
0 GiB
Runtime / backend ·
0.78 GiB
OS / desktop baseline ·
8.00 GiB
Headroom ·
16.0 GiB
Qwen 3.8 Flash
UD-Q6_K_XL at 4K or 32K does not fit every listed card on the calculator.
Minimum system RAM needed
192 GB kit
Estimate · 153.2 GiB raw · 32K context
RAM needed at full context
192 GB kit
Estimate · 159.9 GiB raw · 256K full context
Estimate. Offloaded weights + KV in RAM + runtime + OS/desktop + headroom, rounded up to a 192 GB DIMM kit. The local desktop ships 256 GB DDR5; measured host-RAM usage is not recorded until Local AI numbers arrive.
Breakdown
Offloaded weights ·
125.4 GiB
Separable embed in RAM ·
0 GiB
KV in RAM at selected ·
1.05 GiB
KV in RAM at full context ·
7.61 GiB
Runtime / backend ·
2.78 GiB
OS / desktop baseline ·
8.00 GiB
Headroom ·
16.0 GiB
llama.cpp first
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.
Qwen3.6-35B holds Q4 on one R9700 at 4K. Qwen 3.8 Flash needs RAM offload.
Coding agents
Coding agents want the file in VRAM and a stable llama.cpp server. The house daily-driver recipe is measured on the R9700 for Qwen3.6-35B. Qwen 3.8 Flash is 125B total / 6B active — size Q4 on the calculator before you assume that recipe applies. We do not invent an agent decode figure for Qwen 3.8 Flash.
Long context
Cited context is 262,144 tokens vs 262,144 tokens. KV grows with context. Q4 at 32K fits Qwen3.6-35B and spills on Qwen 3.8 Flash on one R9700. Read /long-context for measured R9700 35B 128K–262K cards. We do not invent a 128K decode figure here.
Size and VRAM
Qwen3.6-35B files: Q6_K 26.7 GB, UD-Q5_K_XL 26.6 GB, Q4_K_M 19.8 GB. Qwen 3.8 Flash files: UD-Q6_K_XL 169 GB, UD-Q5_K_XL 158.3 GB, UD-Q4_K_XL 111 GB. Fit on the four existing GPU sheets below. Empty speed cells stay not measured yet.
Stack Lab
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
.
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
.
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
.
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
.
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
.
Email only — no account. Double opt-in. About once a week, and only when run cards, guides, ROCm problems, or Stack Lab actually changed. Not a daily drip.
Issues may include one labeled Sponsored mention.
Slots and rates:
Sponsor.